4 citations · 8 across the 22 of their papers we have counts for
25 papers
Harness-Delta Attribution: Dissecting Gains From Harness Evolution
Wenxuan Ding, Qin Lu, Changlong Yu +5
Harness evolution automatically optimizes the prompts, skills, tools, and orchestration code around a fixed-weight model, offering a way to improve agentic systems without updating…
Improving LLMs via Validator-to-Generator Alignment
Juan Diego Rodriguez, Jocelyn Zhang, Katrin Erk +1
Large language models are inconsistent: varying prompts or including unrelated information can lead to unexpected changes in model outputs. The generator-validator (G-V) gap is one…
Visually Grounded Self-Reflection for Vision-Language Models via Reinforcement Learning
Liyan Tang, Fangcong Yin, Greg Durrett
Large vision-language models can reason over multimodal inputs by generating textual chains of thought (CoT). A key capability exhibited in CoT reasoning is self-reflection: revisi…
GENIE: A Fine-Grained Measure for Novelty
Ramya Namuduri, Manya Wadhwa, Anshun Asher Zheng +2
Large Language Models have consistently demonstrated a lack of creativity and diversity across tasks. Prior work has focused on addressing whether models are capable of generating…
VESTA: Visual Exploration with Statistical Tool Agents
William Rudman, Abhishek Divekar, Kanishk Jain +6
Fitting quantitative models to data is a central step in scientific workflows, yet it remains one of the least automated. Recent agent-based systems leverage language and vision-la…
Randomized YaRN Improves Length Generalization for Long-Context Reasoning
Manas Mehta, Fangcong Yin, Greg Durrett
Large language models (LLMs) are typically pretrained on short sequences and then extended to work on longer sequences with additional training. However, such LLMs still struggle t…
Detecting and Suppressing Reward Hacking with Gradient Fingerprints
Songtao Wang, Quang Hieu Pham, Fangcong Yin +4
Reinforcement learning with verifiable rewards (RLVR) typically optimizes for outcome rewards without imposing constraints on intermediate reasoning. This leaves training susceptib…
CREATE: Testing LLMs for Associative Creativity
Manya Wadhwa, Tiasa Singha Roy, Harvey Lederman +2
A key component of creativity is associative reasoning: the ability to draw novel yet meaningful connections between concepts. We introduce CREATE, a benchmark designed to evaluate…
VeriSoftBench: Repository-Scale Formal Verification Benchmarks for Lean
Yutong Xin, Qiaochu Chen, Greg Durrett +1
Large language models have achieved striking results in interactive theorem proving, particularly in Lean. However, most benchmarks for LLM-based proof automation are drawn from ma…
Calibrate-Then-Act: Cost-Aware Exploration in LLM Agents
Wenxuan Ding, Nicholas Tomlin, Greg Durrett
LLM agents are deployed in environments where they must interact to acquire information. In these scenarios, the agent must reason about inherent cost-uncertainty tradeoffs in how…
SkillFactory: Self-Distillation For Learning Cognitive Behaviors
Zayne Sprague, Jack Lu, Manya Wadhwa +3
Reasoning models leveraging long chains of thought employ various cognitive skills, such as verification of their answers, backtracking, retrying by an alternate method, and more.…
Adaptive Margin RLHF via Preference over Preferences
Yaswanth Chittepu, Prasann Singhal, Greg Durrett +1
Margin-based optimization is fundamental to improving generalization and robustness in classification tasks. In the context of reward model learning from preferences within Reinfor…
Report on NSF Workshop on Science of Safe AI
Rajeev Alur, Greg Durrett, Hadas Kress-Gazit +2
Recent advances in machine learning, particularly the emergence of foundation models, are leading to new opportunities to develop technology-based solutions to societal problems. H…
PropMEND: Hypernetworks for Knowledge Propagation in LLMs
Zeyu Leo Liu, Greg Durrett, Eunsol Choi
Knowledge editing techniques for large language models (LLMs) can inject knowledge that is later reproducible verbatim, but they fall short on propagating that knowledge: models ca…
Causal Graph based Event Reasoning using Semantic Relation Experts
Mahnaz Koupaee, Xueying Bai, Mudan Chen +3
Understanding how events in a scenario causally connect with each other is important for effectively modeling and reasoning about events. But event reasoning remains a difficult ch…
OpenThoughts: Data Recipes for Reasoning Models
Etash Guha, Ryan Marten, Sedrick Keh +47
Reasoning models have made rapid progress on many benchmarks involving math, code, and science. Yet, there are still many open questions about the best training recipes for reasoni…
SPARTA ALIGNMENT: Collectively Aligning Multiple Language Models through Combat
Yuru Jiang, Wenxuan Ding, Shangbin Feng +2
We propose SPARTA ALIGNMENT, an algorithm to collectively align multiple LLMs through competition and combat. To complement a single model's lack of diversity in generation and bia…
Learning Composable Chains-of-Thought
Fangcong Yin, Zeyu Leo Liu, Liu Leqi +2
A common approach for teaching large language models (LLMs) to reason is to train on chain-of-thought (CoT) traces of in-distribution reasoning problems, but such annotated data is…
ChartMuseum: Testing Visual Reasoning Capabilities of Large Vision-Language Models
Liyan Tang, Grace Kim, Xinyu Zhao +12
Chart understanding presents a unique challenge for large vision-language models (LVLMs), as it requires the integration of sophisticated textual and visual reasoning capabilities.…
RankAlign: A Ranking View of the Generator-Validator Gap in Large Language Models
Juan Diego Rodriguez, Wenxuan Ding, Katrin Erk +1
Although large language models (LLMs) have become more capable and accurate across many tasks, some fundamental sources of unreliability remain in their behavior. One key limitatio…
Is the Top Still Spinning? Evaluating Subjectivity in Narrative Understanding
Melanie Subbiah, Akankshya Mishra, Grace Kim +3
Determining faithfulness of a claim to a source document is an important problem across many domains. This task is generally treated as a binary judgment of whether the claim is su…
LongProc: Benchmarking Long-Context Language Models on Long Procedural Generation
Xi Ye, Fangcong Yin, Yinghui He +5
Existing benchmarks for evaluating long-context language models (LCLMs) primarily focus on long-context recall, requiring models to produce short responses based on a few critical…
Understanding Synthetic Context Extension via Retrieval Heads
Xinyu Zhao, Fangcong Yin, Greg Durrett
Long-context LLMs are increasingly in demand for applications such as retrieval-augmented generation. To defray the cost of pretraining LLMs over long contexts, recent work takes a…
Molecular Facts: Desiderata for Decontextualization in LLM Fact Verification
Anisha Gunjal, Greg Durrett
Automatic factuality verification of large language model (LLM) generations is becoming more and more widely used to combat hallucinations. A major point of tension in the literatu…