cs.CL（2025-04-05）

📊 共 14 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (12 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (12 篇)

#题目一句话要点标签🔗⭐
1 Sensitivity Meets Sparsity: The Impact of Extremely Sparse Parameter Patterns on Theory-of-Mind of Large Language Models 揭示极稀疏参数模式对大语言模型心智理论的影响 large language model
2 Efficient Evaluation of Large Language Models via Collaborative Filtering 提出基于协同过滤的LLM高效评估方法，降低推理开销并准确预估模型性能 large language model
3 A Perplexity and Menger Curvature-Based Approach for Similarity Evaluation of Large Language Models 提出一种基于困惑度和门格尔曲率的大语言模型相似性评估方法 large language model ✅
4 TALLMesh: a simple application for performing Thematic Analysis with Large Language Models TALLMesh：利用大语言模型辅助主题分析的简易应用 large language model
5 GlotEval: A Test Suite for Massively Multilingual Evaluation of Large Language Models GlotEval：大规模多语种大语言模型评测基准 large language model
6 STEP: Staged Parameter-Efficient Pre-training for Large Language Models 提出STEP：一种用于大规模语言模型的阶段式参数高效预训练方法 large language model
7 Self-Adaptive Cognitive Debiasing for Large Language Models in Decision-Making 提出自适应认知偏差消除方法SACD，提升大语言模型在决策场景中的可靠性。 large language model
8 Could AI Trace and Explain the Origins of AI-Generated Images and Text? 提出AI-FAKER数据集，用于追踪和解释AI生成图像和文本的来源模型。 large language model multimodal
9 Towards Understanding and Improving Refusal in Compressed Models via Mechanistic Interpretability 通过可解释性提升压缩模型拒绝回答能力，保障模型安全性 large language model
10 VocalNet: Speech LLM with Multi-Token Prediction for Faster and High-Quality Generation VocalNet：基于多Token预测的语音LLM，加速高质量语音生成 large language model ✅
11 FISH-Tuning: Enhancing PEFT Methods with Fisher Information FISH-Tuning：利用Fisher信息增强参数高效微调方法 large language model
12 OpenCodeInstruct: A Large-scale Instruction Tuning Dataset for Code LLMs OpenCodeInstruct：一个用于代码大语言模型的大规模指令调优数据集 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#题目一句话要点标签🔗⭐
13 An Explicit Syllogistic Legal Reasoning Framework for Large Language Models SyLeR框架：提升大语言模型在法律推理中显式、可解释的能力 reinforcement learning large language model
14 Rethinking Multilingual Continual Pretraining: Data Mixing for Adapting LLMs Across Languages and Resources 研究多语言持续预训练中数据混合策略，提升LLM跨语言和资源适应性。 representation learning large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页