Publications

Empirical Inference Conference Paper Neural Posterior Estimation of Terrain Parameters from Radar Sounder Data Dal Corso, J., Kofler, A., Cortellazzi, M., Bruzzone, L., Schölkopf, B. IEEE International Geoscience and Remote Sensing Symposium (IGARSS), August 2026 (Accepted) arXiv BibTeX

Empirical Inference Conference Paper Echoes of the Prior: A Computational Phenomenology of Forgetting Gao, G., Schölkopf, B., Geiger, A. Proceedings of the ACM on Computer Graphics and Interactive Techniques: PACM-CGIT, SIGGRAPH, July 2026 (Accepted) Project BibTeX

Empirische Inferenz Conference Paper On the Emergence and Test-Time Use of Structural Information in Large Language Models Chen, M. C., Miller, M., Schölkopf, B., Guo, S. 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026), July 2026 (Accepted) arXiv BibTeX

Empirical Inference Article Flexible Gravitational-Wave Parameter Estimation with Transformers Kofler, A., Dax, M., Green, S. R., Wildberger, J., Gupte, N., Macke, J. H., Gair, J., Buonanno, A., Schölkopf, B. Physical Review Letters, May 2026 (Accepted)

Abstract ›

Gravitational-wave data analysis relies on accurate and efficient methods to extract physical information from noisy detector signals, yet the increasing rate and complexity of observations represent a growing challenge. Deep learning provides a powerful alternative to traditional inference, but existing neural models typically lack the flexibility to handle variations in data analysis settings. Such variations accommodate imperfect observations or are required for specialized tests, and could include changes in detector configurations, overall frequency ranges, or localized cuts. We introduce a flexible transformer-based architecture paired with a training strategy that enables adaptation to diverse analysis settings at inference time. Applied to parameter estimation, we demonstrate that a single flexible model—called Dingo-T1—can (i) analyze 48 binary black holes from the third LIGO-Virgo-KAGRA Observing Run under a wide range of analysis configurations, (ii) enable systematic studies of how detector and frequency configurations impact inferred posteriors, and (iii) perform inspiral-merger-ringdown consistency tests probing general relativity. Dingo-T1 also improves median sample efficiency on real events from a baseline of 1.4% to 4.2%. Our approach thus demonstrates flexible and scalable inference with a principled framework for handling missing or incomplete data—key capabilities for current and next-generation observatories.

arXiv DOI URL BibTeX

Empirical Inference Conference Paper Differentiable Simulation of Hard Contacts with Soft Gradients for Learning and Control Paulus*, A., Geist*, A. R., Schumacher*, P., Rappenecker, S., Musil, V., Martius, G. The Fourteenth International Conference on Learning Representations (ICLR), April 2026, *equal contribution (Published) arXiv URL BibTeX

Empirical Inference Conference Paper Estimating Joint Interventional Distributions from Marginal Interventional Data Garrido Mejia, S., Kirschbaum, E., Kekić, A., Schölkopf, B., Mastakouri, A. A. Proceedings of the Fifth Conference on Causal Learning and Reasoning, 323:1-23, PMLR, 5th Conference on Causal Learning and Reasoning, April 2026 (To be published) arXiv BibTeX

Empirical Inference Conference Paper Learning Nonlinear Causal Reductions to Explain Reinforcement Learning Policies Kekić, A., Schneider, J., Büchler, D., Schölkopf*, B., Besserve*, M. The Fourteenth International Conference on Learning Representations (ICLR), April 2026, *joint supervision (Published) arXiv URL BibTeX

Empirical Inference Conference Paper Making Complex Reasoning Student-Friendly: A Hybrid LLM-to-SLM Distillation Framework Yang, Y., He, Y., Liu, J., Jin, Z. 1st Workshop on Scaling Post-training for LLMs at the Fourteenth International Conference on Learning Representations (ICLR), SPOT@ICLR, April 2026 (Published) URL BibTeX

Empirical Inference Conference Paper Position: Science is Collaborative—LLM for Science Should Be Too Zhang, T. J., Jiang, W., Guzman Piedrahita, D., Yang, Y., Lu, S., Schölkopf, B., Jin, Z. ICLR 2026 – 2nd Workshop on Foundation Models for Science: Real-World Impact and Science-First Design , ICLR - Workshop FM4Science, April 2026 (Published) URL BibTeX

Empirical Inference Conference Paper Proper Velocity Neural Networks Chen*, Z., Su*, Z., Schölkopf, B., Sebe, N. The Fourteenth International Conference on Learning Representations (ICLR), April 2026, *equal contribution (Published) URL BibTeX

Empirical Inference Conference Paper Rigidity-Aware Geometric Pretraining for Protein Design and Conformational Ensembles Ni*, Z., Li*, Y., Qiu*, Z., Schölkopf, B., Guo, H., Liu, W., Liu, S. The Fourteenth International Conference on Learning Representations (ICLR), April 2026, *equal contribution (Published) arXiv URL BibTeX

Empirical Inference Conference Paper STRIDE: Training Data Attribution Can Be Estimated In Activation Space Harrasse, A., Dagli, R., Abdullah, A., Jin, Z. ICLR 2026 Workshop on Scientific Methods for Understanding Deep Learning (Sci4DL), Sci4DL at ICLR, April 2026 (Published) URL BibTeX

Empirical Inference Deep Models and Optimization Conference Paper Scaling Behavior of Discrete Diffusion Language Models von Rütte, D., Fluri, J., Pooladzandi, O., Schölkopf, B., Hofmann, T., Orvieto, A. The Fourteenth International Conference on Learning Representations (ICLR), April 2026 (Published) arXiv URL BibTeX

Empirical Inference Robust Machine Learning Conference Paper Skill Learning via Policy Diversity Yields Identifiable Representations for Reinforcement Learning Reizinger*, P., Mucsányi*, B., Guo*, S., Eysenbach, B., Schölkopf, B., Brendel, W. The Fourteenth International Conference on Learning Representations (ICLR), April 2026, *equal contribution (Published) arXiv URL BibTeX

Empirical Inference Conference Paper SocialHarmBench: Revealing LLM Vulnerabilities to Socially Harmful Requests Pandey, P. S., Le, H. S., Bhardwaj, D., Mihalcea, R., Zhijing, J. The Fourteenth International Conference on Learning Representations (ICLR), April 2026 (Published) arXiv URL BibTeX

Empirical Inference Conference Paper Training with Honeypots: Reshaping How LLMs Fail Simko, S., Pandey, P. S., Jin, Z., Schölkopf, B. ICLR 2026 Workshop on Principled Design for Trustworthy AI - Interpretability, Robustness, and Safety across Modalities, ICLR 2026 Trustworthy AI, April 2026 (Published) URL BibTeX

Empirical Inference Conference Paper Democratic or Authoritarian? Probing a New Dimension of Political Biases in Large Language Models Guzman Piedrahita*, D., Strauss*, I., Schölkopf, B., Mihalcea, R., Jin, Z. Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), 593-652, (Editors: Demberg, Vera and Inui, Kentaro and Marquez, Lluís), Association for Computational Linguistics, 19th Conference of the European Chapter of the Association for Computational Linguistics (EACL), March 2026, *equal contribution (Published) DOI URL BibTeX

Empirical Inference Ph.D. Thesis Empirical Likelihood Estimators for Robust and Causal Learning Kremer, H. Eberhard Karls Universität Tübingen, March 2026 (Published) BibTeX

Empirical Inference Conference Paper How Robust Are Router-LLMs? Analysis of the Fragility of LLM Routing Capabilities Kassem, A. M., Schölkopf, B., Jin, Z. Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), 7496-7507, (Editors: Demberg, Vera and Inui, Kentaro and Marquez, Lluís), Association for Computational Linguistics, 19th Conference of the European Chapter of the Association for Computational Linguistics (EACL), March 2026 (Published) DOI URL BibTeX

Empirical Inference Conference Paper Sim-to-Real for Muscle-Actuated Robots via Learned Actuator Models Schneider, J., Mahajan, M., Chen, L., Guist, S., Schölkopf, B., Posner, I., Büchler, D. 2nd German Robotics Conference (GRC), March 2026 (Published) URL BibTeX

Empirical Inference Conference Paper Taming Object Hallucinations with Verified Atomic Confidence Estimation Liu, J., Xuan, W., Jin, Z., Diab, M. T. Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), 5430-5444, (Editors: Demberg, Vera and Inui, Kentaro and Marquez, Lluís), Association for Computational Linguistics, 19th Conference of the European Chapter of the Association for Computational Linguistics (EACL), March 2026 (Published) DOI URL BibTeX

Empirical Inference Conference Paper Uncovering Hidden Correctness in LLM Causal Reasoning via Symbolic Verification He, P., Huang, Y., Sachan, M., Jin, Z. Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), 1231-1250, (Editors: Demberg, Vera and Inui, Kentaro and Marquez, Lluís), Association for Computational Linguistics, 19th Conference of the European Chapter of the Association for Computational Linguistics (EACL), March 2026 (Published) DOI URL BibTeX

Empirical Inference Conference Paper When Do Language Models Endorse Limitations on Human Rights Principles? Samway, K., Takagi, M. N., Mihalcea, R., Schölkopf, B., Chalkidis, I., Hershcovich, D., Jin, Z. Findings of the Association for Computational Linguistics: EACL, 6597-6623, (Editors: Demberg, Vera and Inui, Kentaro and Marquez, Lluís), Association for Computational Linguistics, 19th Conference of the European Chapter of the Association for Computational Linguistics (EACL), March 2026 (Published) DOI URL BibTeX

Empirical Inference Conference Paper CORE: Measuring Multi-Agent LLM Interaction Quality under Game-Theoretic Pressures Pandey, P. S., Yang, Y., Liu, J., Jin, Z. Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), 1251-1266, (Editors: Demberg, Vera and Inui, Kentaro and Marquez, Lluís), Association for Computational Linguistics, 19th Conference of the European Chapter of the Association for Computational Linguistics (EACL), March 2026 (Published) DOI URL BibTeX

Empirical Inference Conference Paper NLP for Social Good: A Survey and Outlook of Challenges, Opportunities and Responsible Deployment Karamolegkou, A., Borah, A., Cho, E., Choudhury, S. R., Galletti, M., Gupta, P., Ignat, O., Kargupta, P., Kotonya, N., Lamba, H., Lee, S., Mangla, A., Mondal, I., Moudakir, F. Z., Nazar, D., Nemkova, P., Pisarevskaya, D., Rizwan, N., Sabri, N., Samway, K., et al. Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), 5110-5170, (Editors: Demberg, Vera and Inui, Kentaro and Marquez, Lluís), Association for Computational Linguistics, 19th Conference of the European Chapter of the Association for Computational Linguistics (EACL), March 2026 (Published) DOI URL BibTeX

Empirical Inference Article Imagining and building wise machines: the centrality of AI metacognition Johnson, S. G. B., Karimi, A., Bengio, Y., Chater, N., Gerstenberg, T., Larson, K., Levine, S., Mitchell, M., Rahwan, I., Schölkopf, B., Grossmann, I. Trends in Cognitive Sciences, February 2026 (Published)

Abstract ›

Although artificial intelligence (AI) has become increasingly smart, its wisdom has not kept pace. In this opinion article, we examine what is known about human wisdom and sketch a vision of its AI counterpart. We introduce human wisdom as strategies for solving intractable problems—those outside the scope of analytic techniques—including both ‘object-level’ strategies, such as heuristics (for managing problems), and ‘metacognitive’ strategies, such as intellectual humility, perspective-taking, or context adaptability (for managing object-level task fit). We argue that AI systems particularly struggle with this type of metacognition. Wise metacognition would lead to AI that is more robust to novel environments, explainable to users, cooperative with others, and safer by risking fewer misaligned goals with human users. We discuss how wise AI might be benchmarked, trained, and implemented.

DOI URL BibTeX

Empirical Inference Learning and Dynamical Systems Article A critical perspective on finite sample conformal prediction theory in medical applications Kladny, K., Schölkopf, B., Koch, L., Baumgartner, C. F., Muehlebach, M. Artificial Intelligence in Medicine, 180:103462, 2026 (Published)

Abstract ›

Machine learning (ML) is transforming healthcare, but safe clinical decisions demand reliable uncertainty estimates that standard ML models fail to provide. Conformal prediction (CP) is a popular tool that allows users to turn heuristic uncertainty estimates into uncertainty estimates with statistical guarantees. CP works by converting predictions of a ML model, together with a calibration sample, into prediction sets that are guaranteed to contain the true label with any desired probability. An often cited advantage is that CP theory holds for calibration samples of arbitrary size, suggesting that uncertainty estimates with practically meaningful statistical guarantees can be achieved even if only small calibration sets are available. We question this promise by showing that, although the statistical guarantees hold for calibration sets of arbitrary size, the practical utility of these guarantees does highly depend on the size of the calibration set. This observation is relevant in medical domains because data is often scarce and obtaining large calibration sets is therefore infeasible. We corroborate our critique in an empirical demonstration on a medical image classification task.

arXiv DOI URL BibTeX

Empirical Inference Conference Paper A data and task-constrained mechanistic model of the mouse outer retina shows robustness to contrast variations Kadhim, K. L., Beck, J., Huang, Z., Macke, J. H., Rieke, F., Euler, T., Deistler, M., Berens, P. Advances in Neural Information Processing Systems 38 (NeurIPS 2025), 39th Annual Conference on Neural Information Processing Systems, December 2025 (Accepted) bioRxiv BibTeX

Empirical Inference Conference Paper Are Language Models Efficient Reasoners? A Perspective from Logic Programming Opedal, A., Zengaffinen, Y., Shirakami, H., Pasti, C., Sachan, M., Saparov, A., Cotterell, R., Schölkopf, B. Advances in Neural Information Processing Systems 38 (NeurIPS 2025), 39th Annual Conference on Neural Information Processing Systems, December 2025 (Accepted) arXiv BibTeX

Empirical Inference Conference Paper Autoformalizing Natural Language to First-Order Logic: A Case Study in Logical Fallacy Detection Lalwani*, A., Kim*, T., Chopra, L., Hahn, C., Jin, Z., Sachan, M. Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics, 132-147, (Editors: Kentaro Inui, Sakriani Sakti, Haofen Wang, Derek F. Wong, Pushpak Bhattacharyya, Biplab Banerjee, Asif Ekbal, Tanmoy Chakraborty, Dhirendra Pratap Singh), The Asian Federation of Natural Language Processing and The Association for Computational Linguistics, IJCNLP & AACL, December 2025, *equal contribution (Published)

Abstract ›

Translating natural language into formal language such as First-Order Logic (FOL) is a foundational challenge in NLP with wide-ranging applications in automated reasoning, misinformation tracking, and knowledge validation. In this paper, we introduce Natural Language to First-Order Logic (NL2FOL), a framework to autoformalize natural language to FOL step-by-step using Large Language Models (LLMs). Our approach addresses key challenges in this translation process, including the integration of implicit background knowledge. By leveraging structured representations generated by NL2FOL, we use Satisfiability Modulo Theory (SMT) solvers to reason about the logical validity of natural language statements. We present logical fallacy detection as a case study to evaluate the efficacy of NL2FOL. Being neurosymbolic, our approach also provides interpretable insights into the reasoning process and demonstrates robustness without requiring model fine-tuning or labeled training data. Our framework achieves good performance on multiple datasets{--}on the Logic dataset, NL2FOL achieves an F1-score of 78{\%}, while generalizing effectively to the LogicClimate dataset with an F1-score of 80{\%}.

DOI URL BibTeX

Empirical Inference Conference Paper CauSciBench: Assessing LLM Causal Reasoning for Scientific Research Acharya, S., Zhang, T. J., Kim, A., Haghighat, A., Sun, X., Shrestha, R. B., Mordig, M., Danisman, F., Jose, C., Qi, Y., Cobben, P., Schölkopf, B., Sachan, M., Jin, Z. NeurIPS 2025: 5th Workshop on Mathematical Reasoning and AI (Math-AI) and CauScien Workshop, December 2025 (Published) URL BibTeX

Empirical Inference Conference Paper Counterfactual reasoning: an analysis of in-context emergence Miller, M., Schölkopf, B., Guo, S. Advances in Neural Information Processing Systems 38 (NeurIPS 2025), 39th Annual Conference on Neural Information Processing Systems, December 2025 (Accepted) arXiv BibTeX

Empirical Inference Conference Paper Cultural Alien Sampler: Open-ended art generation balancing originality and coherence Hernandez, A., Yakura, H., Brinkmann, L., Sola, M. C., Alhaija, H. A., Serna, I., Rahaman, N., Schölkopf, B., Rahwan, I. Advances in Neural Information Processing Systems 38 (NeurIPS 2025), 39th Annual Conference on Neural Information Processing Systems, Creative AI Track, December 2025 (Accepted) arXiv BibTeX

Empirical Inference Conference Paper Do-PFN: In-Context Learning for Causal Effect Estimation Robertson*, J., Reuter*, A., Guo, S., Hollmann, N., Hutter, F., Schölkopf, B. Advances in Neural Information Processing Systems 38 (NeurIPS 2025), 39th Annual Conference on Neural Information Processing Systems, December 2025, *equal contribution (Accepted) arXiv BibTeX

Empirical Inference Conference Paper Effortless, Simulation-Efficient Bayesian Inference using Tabular Foundation Models Vetter, J., Gloeckler, M., Gedon, D., Macke, J. H. Advances in Neural Information Processing Systems 38 (NeurIPS 2025), 39th Annual Conference on Neural Information Processing Systems, December 2025 (Accepted) arXiv BibTeX

Empirical Inference Conference Paper FNOPE: Simulation-based inference on function spaces with Fourier Neural Operators Moss, G., Muhle, L. S., Drews, R., Macke, J. H., Schröder, C. Advances in Neural Information Processing Systems 38 (NeurIPS 2025), 39th Annual Conference on Neural Information Processing Systems, December 2025 (Accepted) arXiv BibTeX

Empirical Inference Conference Paper Forecasting in Offline Reinforcement Learning for Non-stationary Environments Ada, S. E., Martius, G., Ugur, E., Oztop, E. In Advances in Neural Information Processing Systems 38 (NeurIPS 2025), 39th Annual Conference on Neural Information Processing Systems, December 2025 (Accepted) arXiv BibTeX

Empirical Inference Conference Paper Identifying multi-compartment Hodgkin-Huxley models with high-density extracellular voltage recordings Tanoh, I. C., Deistler, M., Macke, J. H., Linderman, S. Advances in Neural Information Processing Systems 38 (NeurIPS 2025), 39th Annual Conference on Neural Information Processing Systems, December 2025 (Accepted) arXiv BibTeX

Empirical Inference Conference Paper Quriosity: Analyzing Human Questioning Behavior and Causal Inquiry through Curiosity-Driven Queries Ceraolo*, R., Kharlapenko*, D., Khan*, A., Reymond, A., Mihalcea, R., Schölkopf, B., Sachan, M., Jin, Z. Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics, 534-563, (Editors: Kentaro Inui, Sakriani Sakti, Haofen Wang, Derek F. Wong, Pushpak Bhattacharyya, Biplab Banerjee, Asif Ekbal, Tanmoy Chakraborty, Dhirendra Pratap Singh), The Asian Federation of Natural Language Processing and The Association for Computational Linguistics, IJCNLP & AACL, December 2025, *equal contribution (Published)

Abstract ›

Recent progress in Large Language Model (LLM) technology has changed our role in interacting with these models. Instead of primarily testing these models with questions we already know answers to, we are now using them for queries where the answers are unknown to us, driven by human curiosity. This shift highlights the growing need to understand curiosity-driven human questions {--} those that are more complex, open-ended, and reflective of real-world needs. To this end, we present Quriosity, a collection of 13K naturally occurring questions from three diverse sources: human-to-search-engine queries, human-to-human interactions, and human-to-LLM conversations. Our comprehensive collection enables a rich understanding of human curiosity across various domains and contexts. Our analysis reveals a significant presence of causal questions (up to 42{\%}) in the dataset, for which we develop an iterative prompt improvement framework to identify all causal queries and examine their unique linguistic properties, cognitive complexity and source distribution. We also lay the groundwork for exploring efficient identifiers of causal questions, providing six efficient classification models.

DOI URL BibTeX

Empirical Inference Conference Paper Reparameterized LLM Training via Orthogonal Equivalence Transformation Qiu, Z., Buchholz, S., Xiao, T., Dax, M., Schölkopf, B., Liu, W. Advances in Neural Information Processing Systems 38 (NeurIPS 2025), 39th Annual Conference on Neural Information Processing Systems, December 2025 (Accepted) arXiv BibTeX

Empirical Inference Conference Paper Root Cause Analysis of Outliers with Missing Structural Knowledge Orchard, W. R., Okati, N., Garrido Mejia, S., Blöbaum, P., Janzing, D. Advances in Neural Information Processing Systems 38 (NeurIPS 2025), 39th Annual Conference on Neural Information Processing Systems, December 2025 (Accepted) arXiv BibTeX

Empirical Inference Conference Paper SPARTAN: A Sparse Transformer World Model Attending to What Matters Lei, A., Schölkopf, B., Posner, I. Advances in Neural Information Processing Systems 38 (NeurIPS 2025), 39th Annual Conference on Neural Information Processing Systems, December 2025 (Accepted) arXiv BibTeX

Empirical Inference Conference Paper Agent-to-Agent Theory of Mind: Testing Interlocutor Awareness among Large Language Models Choi*, Y., Li*, C., Yang, Y., Jin, Z. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP), 28895-28928, (Editors: Christodoulopoulos, Christos and Chakraborty, Tanmoy and Rose, Carolyn and Peng, Violet), Association for Computational Linguistics, EMNLP, November 2025, *equal contribution (Published)

Abstract ›

As large language models (LLMs) are increasingly integrated into multi-agent and human-AI systems, understanding their awareness of both self-context and conversational partners is essential for ensuring reliable performance and robust safety. While prior work has extensively studied situational awareness which refers to an LLM’s ability to recognize its operating phase and constraints, it has largely overlooked the complementary capacity to identify and adapt to the identity and characteristics of a dialogue partner. In this paper, we formalize this latter capability as interlocutor awareness and present the first systematic evaluation of its emergence in contemporary LLMs. We examine interlocutor inference across three dimensions—reasoning patterns, linguistic style, and alignment preferences—and show that LLMs reliably identify same-family peers and certain prominent model families, such as GPT and Claude. To demonstrate its practical significance, we develop three case studies in which interlocutor awareness both enhances multi-LLM collaboration through prompt adaptation and introduces new alignment and safety vulnerabilities, including reward-hacking behaviors and increased jailbreak susceptibility. Our findings highlight the dual promise and peril of identity—sensitive behavior in LLMs, underscoring the need for further understanding of interlocutor awareness and new safeguards in multi-agent deployments.

DOI URL BibTeX

Empirical Inference Conference Paper Are Language Models Consequentialist or Deontological Moral Reasoners? Samway, K., Kleiman-Weiner, M., Guzman Piedrahita, D., Mihalcea, R., Schölkopf, B., Jin, Z. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP), 30699-30726, (Editors: Christodoulopoulos, Christos and Chakraborty, Tanmoy and Rose, Carolyn and Peng, Violet), Association for Computational Linguistics, EMNLP, November 2025 (Published)

Abstract ›

As AI systems increasingly navigate applications in healthcare, law, and governance, understanding how they handle ethically complex scenarios becomes critical. Previous work has mainly examined the moral judgments in large language models (LLMs), rather than their underlying moral reasoning process. In contrast, we focus on a large-scale analysis of the moral reasoning traces provided by LLMs. Furthermore, unlike prior work that attempted to draw inferences from only a handful of moral dilemmas, our study leverages over 600 distinct trolley problems as probes for revealing the reasoning patterns that emerge within different LLMs. We introduce and test a taxonomy of moral rationales to systematically classify reasoning traces according to two main normative ethical theories: consequentialism and deontology. Our analysis reveals that LLM chains-of-thought favor deontological principles based on moral obligations, while post-hoc explanations shift notably toward consequentialist rationales that emphasize utility. Our framework provides a foundation for understanding how LLMs process and articulate ethical considerations, an important step toward safe and interpretable deployment of LLMs in high-stakes decision-making environments."

DOI URL BibTeX

Empirical Inference Conference Paper Improving Large Language Model Safety with Contrastive Representation Learning Simko, S., Sachan, M., Schölkopf, B., Jin, Z. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP), 28166-28194, (Editors: Christodoulopoulos, Christos and Chakraborty, Tanmoy and Rose, Carolyn and Peng, Violet), Association for Computational Linguistics, November 2025 (Published) arXiv DOI URL BibTeX

Empirical Inference Conference Paper Orthogonal Finetuning Made Scalable Qiu*, Z., Liu*, W., Weller, A., Schölkopf, B. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP), 31946-31963, (Editors: Christodoulopoulos, Christos and Chakraborty, Tanmoy and Rose, Carolyn and Peng, Violet), Association for Computational Linguistics, EMNLP, November 2025, *equal contribution (Published)

Abstract ›

Orthogonal finetuning (OFT) offers highly parameter-efficient adaptation while preventing catastrophic forgetting, but its high runtime and memory demands limit practical deployment. We identify the core computational bottleneck in OFT as its weight-centric implementation, which relies on costly matrix-matrix multiplications with cubic complexity. To overcome this, we propose OFTv2, an input-centric reformulation that instead uses matrix-vector multiplications (i.e., matrix-free computation), reducing the computational cost to quadratic. We further introduce the Cayley{--}Neumann parameterization, an efficient orthogonal parameterization that approximates the matrix inversion in the Cayley transform via a truncated Neumann series. These modifications allow OFTv2 to achieve up to 10x faster training and 3x lower GPU memory usage without compromising performance. In addition, we extend OFTv2 to support finetuning quantized foundation models and show that it outperforms the popular QLoRA in training stability, efficiency, and memory usage.

DOI URL BibTeX

Empirical Inference Article In silico biological discovery with large perturbation models Miladinovic*, D., Höppe*, T., Chevalley, M., Georgiou, A., Stuart, L., Mehrjou, A., Bantscheff, M., Schölkopf, B., Schwab, P. Nature Computational Science, October 2025, *equal contribution (Published)

Abstract ›

Data generated in perturbation experiments link perturbations to the changes they elicit and therefore contain information relevant to numerous biological discovery tasks—from understanding the relationships between biological entities to developing therapeutics. However, these data encompass diverse perturbations and readouts, and the complex dependence of experimental outcomes on their biological context makes it challenging to integrate insights across experiments. Here we present the large perturbation model (LPM), a deep-learning model that integrates multiple, heterogeneous perturbation experiments by representing perturbation, readout and context as disentangled dimensions. LPM outperforms existing methods across multiple biological discovery tasks, including in predicting post-perturbation transcriptomes of unseen experiments, identifying shared molecular mechanisms of action between chemical and genetic perturbations, and facilitating the inference of gene–gene interaction networks. LPM learns meaningful joint representations of perturbations, readouts and contexts, enables the study of biological relationships in silico and could considerably accelerate the derivation of insights from pooled perturbation experiments.

DOI URL BibTeX

Empirical Inference Conference Paper Corrupted by reasoning: Reasoning language models become free-riders in public goods games Guzman Piedrahita, D., Yang, Y., Sachan, M., Ramponi, G., Schölkopf, B., Jin, Z. Second Conference on Language Modeling (COLM 2025), October 2025 (Published) arXiv URL BibTeX

Haptic Intelligence Autonomous Learning Empirical Inference Conference Paper Adding Internal Audio Sensing to Internal Vision Enables Human-Like In-Hand Fabric Recognition with Soft Robotic Fingertips Andrussow, I., Solano, J., Richardson, B. A., Martius, G., Kuchenbecker, K. J. In Proceedings of the IEEE-RAS International Conference on Humanoid Robots (Humanoids), 373-380, Seoul, South Korea, September 2025 (Published)

Abstract ›

Distinguishing the feel of smooth silk from coarse cotton is a trivial everyday task for humans. When exploring such fabrics, fingertip skin senses both spatio-temporal force patterns and texture-induced vibrations that are integrated to form a haptic representation of the explored material. It is challenging to reproduce this rich, dynamic perceptual capability in robots because tactile sensors typically cannot achieve both high spatial resolution and high temporal sampling rate. In this work, we present a system that can sense both types of haptic information, and we investigate how each type influences robotic tactile perception of fabrics. Our robotic hand's middle finger and thumb each feature a soft tactile sensor: one is the open- source Minsight sensor that uses an internal camera to measure fingertip deformation and force at 50 Hz, and the other is our new sensor Minsound that captures vibrations through an internal MEMS microphone with a bandwidth from 50 Hz to 15 kHz. Inspired by the movements humans make to evaluate fabrics, our robot actively encloses and rubs folded fabric samples between its two sensitive fingers. Our results test the influence of each sensing modality on overall classification performance, showing high utility for the audio-based sensor. Our transformer-based method achieves a maximum fabric classification accuracy of 97% on a dataset of 20 common fabrics. Incorporating an external microphone away from Minsound increases our method's robustness in loud ambient noise conditions. To show that this audio-visual tactile sensing approach generalizes beyond the training data, we learn general representations of fabric stretchiness, thickness, and roughness.

DOI BibTeX

Empirical Inference Conference Paper Active Fine-Tuning of Multi-Task Policies Bagatella, M., Hübotter, J., Martius, G., Krause, A. In Proceedings of the 42nd International Conference on Machine Learning (ICML), 267:2409-2441, Proceedings of Machine Learning Research, (Editors: Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry), PMLR, International Conference on Machine Learning, July 2025 (Published) arXiv URL BibTeX

Publications

Filter by