6 papers · 1 filter
Not Just the Destination, But the Journey: Reasoning Traces Causally Shape Generalization Behaviors
Pengcheng Wen, Yanxu Zhu, Jiapeng Sun +5
Chain-of-Thought (CoT) is often viewed as a window into LLM decision-making, yet recent work suggests it may function merely as post-hoc rationalization. This raises a critical ali…
DC-W2S: Dual-Consensus Weak-to-Strong Training for Reliable Process Reward Modeling in Biological Reasoning
Chi-Min Chan, Ehsan Hajiramezanali, Xiner Li +6
In scientific reasoning tasks, the veracity of the reasoning process is as critical as the final outcome. While Process Reward Models (PRMs) offer a solution to the coarse-grained…
SafeMT: Multi-turn Safety for Multimodal Language Models
Han Zhu, Juntao Dai, Jiaming Ji +8
With the widespread use of multi-modal Large Language models (MLLMs), safety issues have become a growing concern. Multi-turn dialogues, which are more common in everyday interacti…
Semantic Voting: A Self-Evaluation-Free Approach for Efficient LLM Self-Improvement on Unverifiable Open-ended Tasks
Chunyang Jiang, Yonggang Zhang, Yiyang Cai +5
The rising cost of acquiring supervised data has driven significant interest in self-improvement for large language models (LLMs). Straightforward unsupervised signals like majorit…
Graceful Forgetting in Generative Language Models
Chunyang Jiang, Chi-min Chan, Yiyang Cai +3
Recently, the pretrain-finetune paradigm has become a cornerstone in various deep learning areas. While in general the pre-trained model would promote both effectiveness and effici…
ThinkPatterns-21k: A Systematic Study on the Impact of Thinking Patterns in LLMs
Pengcheng Wen, Jiaming Ji, Chi-Min Chan +5
Large language models (LLMs) have demonstrated enhanced performance through the \textit{Thinking then Responding} paradigm, where models generate internal thoughts before final res…