11 papers
When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs
Omatharv Bharat Vaidya, Connor Thomas Jerzak, Zayne Rea Sprague +2
Self-consistency assumes the most frequent answer among sampled reasoning traces is the most reliable, but this can fail in causal reasoning: samples often repeat the same confound…
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…
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…
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.…
Query-Focused Retrieval Heads Improve Long-Context Reasoning and Re-ranking
Wuwei Zhang, Fangcong Yin, Howard Yen +2
Recent work has identified retrieval heads, a subset of attention heads responsible for retrieving salient information in long-context language models (LMs), as measured by their c…