cs.CL（2025-09-08）

📊 共 17 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (14 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (14 篇)

#题目一句话要点标签🔗⭐
1 The Thinking Therapist: Training Large Language Models to Deliver Acceptance and Commitment Therapy using Supervised Fine-Tuning and Odds Ratio Policy Optimization 利用监督微调和优势比策略优化训练大语言模型进行接受与承诺疗法 large language model chain-of-thought
2 Towards EnergyGPT: A Large Language Model Specialized for the Energy Sector 提出EnergyGPT，一个针对能源领域的专业大型语言模型，通过微调LLaMA 3.1-8B实现。 large language model
3 Toward Purpose-oriented Topic Model Evaluation enabled by Large Language Models 提出基于大语言模型的面向目的性主题模型评估框架，解决传统指标语义理解不足的问题。 large language model ✅
4 MedBench-IT: A Comprehensive Benchmark for Evaluating Large Language Models on Italian Medical Entrance Examinations MedBench-IT：首个意大利医学入学考试LLM综合评测基准 large language model
5 EPT Benchmark: Evaluation of Persian Trustworthiness in Large Language Models 提出EPT基准，评估大型语言模型在波斯语环境下的可信度 large language model ✅
6 A Comparative Benchmark of Large Language Models for Labelling Wind Turbine Maintenance Logs 提出风机维护日志标注的LLM基准测试框架，加速运维数据分析。 large language model
7 LLM Analysis of 150+ years of German Parliamentary Debates on Migration Reveals Shift from Post-War Solidarity to Anti-Solidarity in the Last Decade 利用LLM分析德国议会百年辩论，揭示从战后团结到反团结的转变 large language model
8 Neurocognitive Modeling for Text Generation: Deep Learning Architecture for EEG Data 提出基于RNN编码器和Gemma 2B的分类器-LLM架构，用于脑电信号文本生成。 large language model
9 On the Same Wavelength? Evaluating Pragmatic Reasoning in Language Models across Broad Concepts 提出基于Wavelength的评估框架，衡量语言模型在广泛概念上的语用推理能力。 chain-of-thought
10 Proof-Carrying Numbers (PCN): A Protocol for Trustworthy Numeric Answers from LLMs via Claim Verification 提出Proof-Carrying Numbers以解决LLMs数值可信性问题 large language model
11 COMPACT: Common-token Optimized Model Pruning Across Channels and Tokens COMPACT：面向通道和Token的通用Token优化模型剪枝，提升小模型性能。 large language model
12 Saturation-Driven Dataset Generation for LLM Mathematical Reasoning in the TPTP Ecosystem 利用饱和驱动的数据集生成方法，提升LLM在TPTP生态中的数学推理能力 large language model ✅
13 MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security MoGU V2：提升LLM可用性与安全性帕累托前沿的框架 large language model
14 Anchoring Refusal Direction: Mitigating Safety Risks in Tuning via Projection Constraint 提出ProCon方法，通过投影约束缓解指令微调中大语言模型的安全性风险。 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
15 Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models 提出TraceRL，一种轨迹感知的扩散语言模型强化学习框架，提升推理性能。 reinforcement learning curriculum learning large language model ✅
16 Beyond Two-Stage Training: Cooperative SFT and RL for LLM Reasoning 提出Cooperative SFT and RL方法，解决LLM推理中SFT与RL训练的灾难性遗忘问题 reinforcement learning large language model
17 The Majority is not always right: RL training for solution aggregation 提出AggLM，通过强化学习训练聚合模型，提升LLM在推理任务中的表现。 reinforcement learning large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页