cs.CL（2025-03-22）

📊 共 6 篇论文

🎯 兴趣领域导航

#	题目	一句话要点	标签
1	Think Before Refusal : Triggering Safety Reflection in LLMs to Mitigate False Refusal Behavior	提出Think-Before-Refusal框架，缓解大语言模型中的错误拒绝行为	large language model
2	Feather-SQL: A Lightweight NL2SQL Framework with Dual-Model Collaboration Paradigm for Small Language Models	Feather-SQL：面向小语言模型的轻量级NL2SQL框架，采用双模型协作范式	large language model
3	Improving Preference Extraction In LLMs By Identifying Latent Knowledge Through Classifying Probes	提出基于分类探针的偏好提取方法，提升LLM作为评估者的准确性和效率	large language model
4	Building Resource-Constrained Language Agents: A Korean Case Study on Chemical Toxicity Information	针对资源受限场景，提出韩语化学毒性信息智能体Tox-chat	large language model
5	Enhancing Arabic Automated Essay Scoring with Synthetic Data and Error Injection	利用合成数据和错误注入增强阿拉伯语自动作文评分系统	large language model

#	题目	一句话要点	标签	🔗	⭐
6	Enhancing Persona Consistency for LLMs' Role-Playing using Persona-Aware Contrastive Learning	提出Persona-Aware Contrastive Learning以提升LLM角色扮演一致性	reinforcement learning RLHF contrastive learning