8 citations · 26 across the 32 of their papers we have counts for
9 papers · 1 filter
Better LLM Reasoning via Dual-Play
Zhengxin Zhang, Chengyu Huang, Aochong Oliver Li +1
Large Language Models (LLMs) have achieved remarkable progress through Reinforcement Learning with Verifiable Rewards (RLVR), yet still rely heavily on external supervision (e.g.,…
Multi-Hop Question Answering: When Can Humans Help, and Where do They Struggle?
Jinyan Su, Claire Cardie, Jennifer Healey
Multi-hop question answering is a challenging task for both large language models (LLMs) and humans, as it requires recognizing when multi-hop reasoning is needed, followed by read…
MASH: Modeling Abstention via Selective Help-Seeking
Mustafa Omer Gul, Claire Cardie, Tanya Goyal
LLMs cannot reliably recognize their parametric knowledge boundaries and often hallucinate answers to outside-of-boundary questions. In this paper, we introduce MASH (Modeling Abst…
Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards
Jinyan Su, Claire Cardie
Large language models (LLMs) have demonstrated strong reasoning abilities in mathematical tasks, often enhanced through reinforcement learning (RL). However, RL-trained models freq…
HAPO: Training Language Models to Reason Concisely via History-Aware Policy Optimization
Chengyu Huang, Zhengxin Zhang, Claire Cardie
While scaling the length of responses at test-time has been shown to markedly improve the reasoning abilities and performance of large language models (LLMs), it often results in v…
Between Underthinking and Overthinking: An Empirical Study of Reasoning Length and correctness in LLMs
Jinyan Su, Jennifer Healey, Preslav Nakov +1
Large language models (LLMs) are increasingly optimized for long reasoning, under the assumption that more reasoning leads to better performance. However, emerging evidence suggest…
Reasoning Court: Combining Reasoning, Action, and Judgment for Multi-Hop Reasoning
Jingtian Wu, Claire Cardie
While large language models (LLMs) have demonstrated strong capabilities in tasks like question answering and fact verification, they continue to suffer from hallucinations and rea…
MedSimAI: Simulation and Formative Feedback Generation to Enhance Deliberate Practice in Medical Education
Yann Hicke, Jadon Geathers, Kellen Vu +8
Medical education faces challenges in providing scalable, consistent clinical skills training. Simulation with standardized patients (SPs) develops communication and diagnostic ski…
Fast or Better? Balancing Accuracy and Cost in Retrieval-Augmented Generation with Flexible User Control
Jinyan Su, Jennifer Healey, Preslav Nakov +1
Retrieval-Augmented Generation (RAG) has emerged as a powerful approach to mitigate large language model (LLM) hallucinations by incorporating external knowledge retrieval. However…