7 papers
When Words Speak Louder than Images: Towards Understanding Language Bias in Vision-Language Models
Yizhou Fang, Siyue Chen, Zimo Qi +3
Despite substantial progress across downstream applications, vision-language models (VLMs) remain susceptible to language bias, often prioritizing linguistic cues over visual evide…
When Humans Leave Context Unsaid: Implicit Context as a Risk for Large Language Models
Bocheng Chen, Han Zi, Yuda Chen +6
Human language is grounded in pragmatics, necessitating implicit (extralinguistic) context to interpret language, e.g., world knowledge and social norms. However, such context is o…
Deactivating Refusal Triggers: Understanding and Mitigating Overrefusal in Safety Alignment
Zhiyu Xue, Zimo Qi, Guangliang Liu +2
Safety alignment aims to ensure that large language models (LLMs) refuse harmful requests by post-training on harmful queries paired with refusal answers. Although safety alignment…
Learning to Diagnose and Correct Moral Errors: Beyond Shallow Heuristics in Moral Alignment
Bocheng Chen, Xi Chen, Han Zi +5
Existing approaches to moral value alignment are primarily set out to align LLMs' generation with the distributions of morally appropriate language, which has seen good progress. H…
Discourse Heuristics For Paradoxically Moral Self-Correction
Guangliang Liu, Zimo Qi, Xitong Zhang +1
Moral self-correction has emerged as a promising approach for aligning the output of Large Language Models (LLMs) with human moral values. However, moral self-correction techniques…
Diagnosing Moral Reasoning Acquisition in Language Models: Pragmatics and Generalization
Guangliang Liu, Zimo Qi, Xitong Zhang +2
Ensuring that Large Language Models (LLMs) return just responses which adhere to societal values is crucial for their broader application. Prior research has shown that LLMs often…
Self-correction is Not An Innate Capability in Language Models
Guangliang Liu, Zimo Qi, Xitong Zhang +2
Although there has been growing interest in the self-correction capability of Large Language Models (LLMs), there are varying conclusions about its effectiveness. Prior research ha…