21 citations · 49 across the 24 of their papers we have counts for
27 papers
AM-Bench: A Unified Taxonomy and Evaluation Suite for Agentic Misalignment
Eric Zhang, Terry Jingchen Zhang, Chijioke Ugwuanyi +3
As LLM-based agents are deployed with increasing autonomy in real-world environments, a critical failure mode emerges: agentic misalignment, where agents choose harmful actions ove…
ABC: Advantage-Based Control Variates for Reinforcement Learning with Verifiable Rewards
Hsiao-Ru Pan, Florent Draye, Bernhard Schölkopf
Recent progress in reinforcement learning with verifiable rewards (RLVR) has highlighted the effectiveness of simple critic-free policy-gradient methods such as Group Relative Poli…
PaperMentor: A Human-Centered Multi-Agent Writing Tutor for AI Research Papers on Overleaf
Jiarui Liu, Terry Jingchen Zhang, Ryan Faulkner +17
Expert writing feedback from experienced researchers is critical for early-career scholars to improve their manuscripts, yet high-quality feedback often remains scarce because revi…
Learning to Reason Efficiently with A* Post-Training
Andreas Opedal, Francesco Ignazio Re, Abulhair Saparov +3
Many applications of large language models (LLMs) require deductive reasoning, yet models frequently produce incorrect or redundant inference steps. We frame natural language infer…
Rethinking Easy-to-Hard: Limits of Curriculum Learning in Post-Training for Deductive Reasoning
Maximilian Mordig, Andreas Opedal, Weiyang Liu +1
Curriculum learning (CL), motivated by the intuition that learning in increasing order of difficulty should ease generalization, is commonly adopted both in pre-training and post-t…
Preserving Historical Truth: Detecting Historical Revisionism in Large Language Models
Francesco Ortu, Joeun Yook, Punya Syon Pandey +5
Large language models (LLMs) are increasingly used as sources of historical information, motivating the need for scalable audits on contested events and politically charged narrati…
LoRA and Privacy: When Random Projections Help (and When They Don't)
Yaxi Hu, Johanna Düngler, Bernhard Schölkopf +1
We introduce the (Wishart) projection mechanism, a randomized map of the form with and study its differential privacy properties. For ve…
Are LLMs Good Safety Agents or a Propaganda Engine?
Neemesh Yadav, Francesco Ortu, Jiarui Liu +5
Large Language Models (LLMs) are trained to refuse to respond to harmful content. However, systematic analyses of whether this behavior is truly a reflection of its safety policies…
Are Language Models Efficient Reasoners? A Perspective from Logic Programming
Andreas Opedal, Yanick Zengaffinen, Haruki Shirakami +5
Modern language models (LMs) exhibit strong deductive reasoning capabilities, yet standard evaluations emphasize correctness while overlooking a key aspect of reasoning: efficiency…
Test of Time: Rethinking Temporal Signal of Benchmark Contamination
Terry Jingchen Zhang, Gopal Dev, Ning Wang +8
Post-cutoff performance decay of LLMs has been widely interpreted as a temporal signal for benchmark contamination, where public information released before the training cutoff may…
Online Learning and Unlearning
Yaxi Hu, Bernhard Schölkopf, Amartya Sanyal
We formalize the problem of online learning-unlearning, where a model is updated sequentially in an online setting while accommodating unlearning requests between updates. After a…
Are Language Models Consequentialist or Deontological Moral Reasoners?
Keenan Samway, Max Kleiman-Weiner, David Guzman Piedrahita +3
As AI systems increasingly navigate applications in healthcare, law, and governance, understanding how they handle ethically complex scenarios becomes critical. Previous work has m…
How Robust Are Router-LLMs? Analysis of the Fragility of LLM Routing Capabilities
Aly M. Kassem, Bernhard Schölkopf, Zhijing Jin
Large language model (LLM) routing has emerged as a crucial strategy for balancing computational costs with performance by dynamically assigning queries to the most appropriate mod…
DARS: Dynamic Action Re-Sampling to Enhance Coding Agent Performance by Adaptive Tree Traversal
Vaibhav Aggarwal, Ojasv Kamal, Abhinav Japesh +2
Large Language Models (LLMs) have revolutionized various domains, including natural language processing, data analysis, and software development, by enabling automation. In softwar…
Causality can systematically address the monsters under the bench(marks)
Felix Leeb, Zhijing Jin, Bernhard Schölkopf
Effective and reliable evaluation is essential for advancing empirical machine learning. However, the increasing accessibility of generalist models and the progress towards ever mo…
MathGAP: Out-of-Distribution Evaluation on Problems with Arbitrarily Complex Proofs
Andreas Opedal, Haruki Shirakami, Bernhard Schölkopf +2
Large language models (LLMs) can solve arithmetic word problems with high accuracy, but little is known about how well they generalize to more complex problems. This is difficult t…
Language Model Alignment in Multilingual Trolley Problems
Zhijing Jin, Max Kleiman-Weiner, Giorgio Piatti +9
We evaluate the moral alignment of LLMs with human preferences in multilingual trolley problems. Building on the Moral Machine experiment, which captures over 40 million human judg…
Accuracy on the wrong line: On the pitfalls of noisy data for out-of-distribution generalisation
Amartya Sanyal, Yaxi Hu, Yaodong Yu +3
"Accuracy-on-the-line" is a widely observed phenomenon in machine learning, where a model's accuracy on in-distribution (ID) and out-of-distribution (OOD) data is positively correl…
On Affine Homotopy between Language Encoders
Robin SM Chan, Reda Boumasmoud, Anej Svete +8
Pre-trained language encoders -- functions that represent text as vectors -- are an integral component of many NLP tasks. We tackle a natural question in language encoder analysis:…
Do LLMs Think Fast and Slow? A Causal Study on Sentiment Analysis
Zhiheng Lyu, Zhijing Jin, Fernando Gonzalez +3
Sentiment analysis (SA) aims to identify the sentiment expressed in a text, such as a product review. Given a review and the sentiment associated with it, this work formulates SA a…
A diverse Multilingual News Headlines Dataset from around the World
Felix Leeb, Bernhard Schölkopf
Babel Briefings is a novel dataset featuring 4.7 million news headlines from August 2020 to November 2021, across 30 languages and 54 locations worldwide with English translations…
Provable Privacy with Non-Private Pre-Processing
Yaxi Hu, Amartya Sanyal, Bernhard Schölkopf
When analysing Differentially Private (DP) machine learning pipelines, the potential privacy cost of data-dependent pre-processing is frequently overlooked in privacy accounting. I…
Skill or Luck? Return Decomposition via Advantage Functions
Hsiao-Ru Pan, Bernhard Schölkopf
Learning from off-policy data is essential for sample-efficient reinforcement learning. In the present work, we build on the insight that the advantage function can be understood a…
CLadder: Assessing Causal Reasoning in Language Models
Zhijing Jin, Yuen Chen, Felix Leeb +8
The ability to perform causal reasoning is widely considered a core feature of intelligence. In this work, we investigate whether large language models (LLMs) can coherently reason…