17 papers
CrossWeave: Bridging Perspectives Across Online Communities with a Dual-Pane Design
Fei Fang, Reva Hirave, William Jurayj +19
Social media systems typically display conversations among already familiar contributors, which can be predictable and one-sided. In civic discourse, this design narrows discussion…
Better, Faster, Stronger: Programmatic Skill Learning Best Reduces Agent Cost
Zixi Huang, Xiheng Wang, Andrew Wang +4
Recently, the practice of augmenting LLM agent capability with skills has gained prevalence. We explore the cost effective adaptation of agents to novel domains by means of learnin…
Self-Compacting Language Model Agents
Tianjian Li, Jingyu Zhang, William Jurayj +5
Long agent traces composed of chains of thought and tool calls accumulate stale content that anchor subsequent generations, and eventually outgrow the context window. Existing scaf…
Rethinking LoRA Memory Through the Lens of KV Cache Compression
Chunsheng Zuo, Liaoyaqi Wang, William Jurayj +2
Parametric retrieval augmentation encodes document information into lightweight, document-specific modules such as LoRA adapters, reducing the need to include all evidence as input…
DAR: Deontic Reasoning with Agentic Harnesses
Guangyao Dou, William Jurayj, Nils Holzenberger +1
Deontic reasoning is the task of answering questions by applying explicit rules and policies to case-specific facts, for example computing tax liability under a statute or determin…
Weird Generalization is Weirdly Brittle
Miriam Wanner, Hannah Collison, William Jurayj +3
Weird generalization is a phenomenon in which models fine-tuned on data from a narrow domain (e.g. insecure code) develop surprising traits that manifest even outside that domain (…
Can Coding Agents Reproduce Findings in Computational Materials Science?
Ziyang Huang, Yi Cao, Ali K. Shargh +15
Large language models are increasingly deployed as autonomous coding agents and have achieved remarkably strong performance on software engineering benchmarks. However, it is uncle…
Unified Multimodal Uncertain Inference
Dengjia Zhang, Alexander Martin, William Jurayj +3
We introduce Unified Multimodal Uncertain Inference (UMUI), a multimodal inference task spanning text, audio, and video, where models must produce calibrated probability estimates…
DeonticBench: A Benchmark for Reasoning over Rules
Guangyao Dou, Luis Brena, Akhil Deo +4
Reasoning with complex, context-specific rules remains challenging for large language models (LLMs). In legal and policy settings, this manifests as deontic reasoning: reasoning ab…
Process Supervision of Confidence Margin for Calibrated LLM Reasoning
Liaoyaqi Wang, Chunsheng Zuo, William Jurayj +2
Scaling test-time computation with reinforcement learning (RL) has emerged as a reliable path to improve large language models (LLM) reasoning ability. Yet, outcome-based reward of…
Many-Tier Instruction Hierarchy in LLM Agents
Jingyu Zhang, Tianjian Li, William Jurayj +3
Large language model agents receive instructions from many sources-system messages, user prompts, tool outputs, other agents, and more-each carrying different levels of trust and a…
Conformal Thinking: Risk Control for Reasoning on a Compute Budget
Xi Wang, Anushri Suresh, Alvin Zhang +6
Reasoning Large Language Models (LLMs) enable test-time scaling, with dataset-level accuracy improving as the token budget increases, motivating adaptive reasoning -- spending toke…
Language Models and Logic Programs for Trustworthy Tax Reasoning
William Jurayj, Nils Holzenberger, Benjamin Van Durme
According to the United States Internal Revenue Service, ``the average American spends and 13 hours filing their taxes''. Even beyond the U.S., tax filing requires complex…
CLAIMCHECK: How Grounded are LLM Critiques of Scientific Papers?
Jiefu Ou, William Gantt Walden, Kate Sanders +13
A core part of scientific peer review involves providing expert critiques that directly assess the scientific claims a paper makes. While it is now possible to automatically genera…
Is That Your Final Answer? Test-Time Scaling Improves Selective Question Answering
William Jurayj, Jeffrey Cheng, Benjamin Van Durme
Scaling the test-time compute of large language models has demonstrated impressive performance on reasoning benchmarks. However, existing evaluations of test-time scaling make the…
Gaps or Hallucinations? Gazing into Machine-Generated Legal Analysis for Fine-grained Text Evaluations
Abe Bohan Hou, William Jurayj, Nils Holzenberger +2
Large Language Models (LLMs) show promise as a writing aid for professionals performing legal analyses. However, LLMs can often hallucinate in this setting, in ways difficult to re…
Garden-Path Traversal in GPT-2
William Jurayj, William Rudman, Carsten Eickhoff
In recent years, large-scale transformer decoders such as the GPT-x family of models have become increasingly popular. Studies examining the behavior of these models tend to focus…