cs.CL（2024-05-23）

📊 共 6 篇论文

🎯 兴趣领域导航

#	题目	一句话要点	标签
1	RE-Adapt: Reverse Engineered Adaptation of Large Language Models	提出RE-Adapt，在不损失指令微调性能前提下，实现LLM在新领域的适应。	large language model instruction following
2	Eliciting Informative Text Evaluations with Large Language Models	提出生成式对等预测机制，利用大语言模型提升文本评价质量。	large language model
3	Aya 23: Open Weight Releases to Further Multilingual Progress	Aya 23：发布开源权重以推进多语言建模进展，覆盖23种语言。	large language model
4	Extracting Prompts by Inverting LLM Outputs	提出output2prompt方法，通过反演LLM输出来提取生成提示词。	zero-shot transfer
5	Linking In-context Learning in Transformers to Human Episodic Memory	揭示Transformer上下文学习与人类情景记忆的关联，发现类CMR机制	large language model

#	题目	一句话要点	标签	🔗	⭐
6	Reframing Spatial Reasoning Evaluation in Language Models: A Real-World Simulation Benchmark for Qualitative Reasoning	提出基于真实3D模拟的语言模型定性空间推理评估基准	spatial relationship