6 papers
Please refuse to answer me! Mitigating Over-Refusal in Large Language Models via Adaptive Contrastive Decoding
Yupeng Qi, Ziyu Lyu, Lixin Cui +2
Safety-aligned large language models (LLMs) often generate refusal responses to harmless queries due to the over-refusal problem. However, existing methods for mitigating over-refu…
Debiasing Large Language Models via Adaptive Causal Prompting with Sketch-of-Thought
Bowen Li, Ziqi Xu, Jing Ren +5
Despite notable advancements in prompting methods for Large Language Models (LLMs), such as Chain-of-Thought (CoT), existing strategies still suffer from excessive token usage and…
Hallucinate Less by Thinking More: Aspect-Based Causal Abstention for Large Language Models
Vy Nguyen, Ziqi Xu, Jeffrey Chan +3
Large Language Models (LLMs) often produce fluent but factually incorrect responses, a phenomenon known as hallucination. Abstention, where the model chooses not to answer and inst…
Unbiased Reasoning for Knowledge-Intensive Tasks in Large Language Models via Conditional Front-Door Adjustment
Bo Zhao, Yinghao Zhang, Ziqi Xu +5
Large Language Models (LLMs) have shown impressive capabilities in natural language processing but still struggle to perform well on knowledge-intensive tasks that require deep rea…
Cultural Bias Matters: A Cross-Cultural Benchmark Dataset and Sentiment-Enriched Model for Understanding Multimodal Metaphors
Senqi Yang, Dongyu Zhang, Jing Ren +5
Metaphors are pervasive in communication, making them crucial for natural language processing (NLP). Previous research on automatic metaphor processing predominantly relies on trai…
Teaching Large Language Models Number-Focused Headline Generation With Key Element Rationales
Zhen Qian, Xiuzhen Zhang, Xiaofei Xu +1
Number-focused headline generation is a summarization task requiring both high textual quality and precise numerical accuracy, which poses a unique challenge for Large Language Mod…