7 papers · 1 filter
Encode Errors: Representational Retrieval of In-Context Demonstrations for Multilingual Grammatical Error Correction
Guangyue Peng, Wei Li, Wen Luo +1
Grammatical Error Correction (GEC) involves detecting and correcting the wrong usage of grammar. While large language models (LLMs) with in-context learning (ICL) capabilities have…
Measuring and Mitigating Post-hoc Rationalization in Reverse Chain-of-Thought Generation
Guangyue Peng, Zongchao Chen, Wen Luo +9
Reverse Chain-of-Thought Generation (RCG) synthesizes reasoning traces from query-answer pairs, but answer-visible generation can justify a pre-committed answer rather than derive…
Two Pathways to Truthfulness: On the Intrinsic Encoding of LLM Hallucinations
Wen Luo, Guangyue Peng, Wei Li +8
Despite their impressive capabilities, large language models (LLMs) frequently generate hallucinations. Previous work shows that their internal states encode rich signals of truthf…
Mitigating Overthinking through Reasoning Shaping
Feifan Song, Shaohang Wei, Bofei Gao +8
Large reasoning models (LRMs) boosted by Reinforcement Learning from Verifier Reward (RLVR) have shown great power in problem solving, yet they often cause overthinking: excessive,…
Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding
Feifan Song, Shaohang Wei, Wen Luo +4
Large Language Models (LLMs) require alignment with human preferences to avoid generating offensive, false, or meaningless content. Recently, low-resource methods for LLM alignment…
Odysseus Navigates the Sirens' Song: Dynamic Focus Decoding for Factual and Diverse Open-Ended Text Generation
Wen Luo, Feifan Song, Wei Li +3
Large Language Models (LLMs) are increasingly required to generate text that is both factually accurate and diverse across various open-ended applications. However, current stochas…