cs.CL（2025-08-11）

📊 共 34 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (26 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (6 🔗1) 支柱六：视频提取与匹配 (Video Extraction) (1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (26 篇)

#题目一句话要点标签🔗⭐
1 CoDAE: Adapting Large Language Models for Education via Chain-of-Thought Data Augmentation 提出CoDAE框架以解决教育场景中LLM适应性不足问题 large language model chain-of-thought
2 Capabilities of GPT-5 on Multimodal Medical Reasoning 提出GPT-5作为多模态医学推理的通用解决方案 large language model multimodal chain-of-thought
3 Evaluating Large Language Models as Expert Annotators 评估大型语言模型作为专家标注者的有效性 large language model chain-of-thought
4 Momentum Point-Perplexity Mechanics in Large Language Models 提出动量点-困惑度机制以研究大语言模型的内部状态变化 large language model
5 Signature vs. Substance: Evaluating the Balance of Adversarial Resistance and Linguistic Quality in Watermarking Large Language Models 评估水印技术在大型语言模型中的对抗抵抗力与语言质量平衡 large language model
6 Echoes of Agreement: Argument Driven Opinion Shifts in Large Language Models 探讨提示对大型语言模型政治偏见的影响 large language model
7 Human-Alignment and Calibration of Inference-Time Uncertainty in Large Language Models 提出人类对齐与推理时不确定性校准方法以提升LLM用户体验 large language model
8 Large Language Models for Czech Aspect-Based Sentiment Analysis 评估大型语言模型在捷克语基于方面的情感分析中的应用 large language model
9 Exploring Causal Effect of Social Bias on Faithfulness Hallucinations in Large Language Models 探讨社会偏见对大型语言模型信实性幻觉的因果影响 large language model
10 What am I missing here?: Evaluating Large Language Models for Masked Sentence Prediction 评估大语言模型在掩码句子预测中的表现以解决长程一致性问题 large language model
11 Assessing LLM Text Detection in Educational Contexts: Does Human Contribution Affect Detection? 提出GEDE数据集以解决教育环境中的LLM文本检测问题 large language model ✅
12 Jinx: Unlimited LLMs for Probing Alignment Failures 提出Jinx以探测语言模型的对齐失败问题 instruction following
13 Efficient Speculative Decoding for Llama at Scale: Challenges and Solutions 提出高效的推测解码方法以解决大规模推理挑战 large language model
14 Can LLMs Detect Their Confabulations? Estimating Reliability in Uncertainty-Aware Language Models 提出基于不确定性引导的探测方法以提高LLM的可靠性 large language model
15 Dual Information Speech Language Models for Emotional Conversations 提出双重信息语音语言模型以解决情感对话中的信息捕捉问题 large language model
16 Progressive Depth Up-scaling via Optimal Transport 提出Optimal Transport深度上采样以解决神经元排列不匹配问题 large language model
17 WideSearch: Benchmarking Agentic Broad Info-Seeking 提出WideSearch基准以评估大规模信息搜索代理的可靠性 large language model
18 Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RL 提出ASearcher以解决长时间搜索智能不足的问题 zero-shot transfer ✅
19 Joint Transcription of Acoustic Guitar Strumming Directions and Chords 提出一种深度学习模型以解决吉他扫弦方向与和弦的自动转录问题 multimodal
20 Punctuation and Predicates in Language Models 探讨标点符号在语言模型中的重要性及推理机制 large language model
21 Can You Trick the Grader? Adversarial Persuasion of LLM Judges 揭示语言模型评估中的说服性偏见问题 large language model
22 Grove MoE: Towards Efficient and Superior MoE LLMs with Adjugate Experts 提出Grove MoE以解决传统MoE模型的计算效率问题 large language model
23 LoSemB: Logic-Guided Semantic Bridging for Inductive Tool Retrieval 提出LoSemB框架以解决工具检索中的分布转移问题 large language model
24 Keyword-Centric Prompting for One-Shot Event Detection with Self-Generated Rationale Enhancements 提出KeyCP++以解决LLM在事件检测中的不足 chain-of-thought
25 IBPS: Indian Bail Prediction System 提出印度保释预测系统以解决司法延误问题 large language model
26 Augmenting Bias Detection in LLMs Using Topological Data Analysis 利用拓扑数据分析增强大语言模型的偏见检测 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (6 篇)

#题目一句话要点标签🔗⭐
27 Audio-Thinker: Guiding Audio Language Model When and How to Think via Reinforcement Learning 提出Audio-Thinker以解决音频语言模型推理能力不足问题 reinforcement learning large language model multimodal
28 Mol-R1: Towards Explicit Long-CoT Reasoning in Molecule Discovery 提出Mol-R1以解决分子发现中的长链推理问题 distillation large language model chain-of-thought
29 Steerable Pluralism: Pluralistic Alignment via Few-Shot Comparative Regression 提出可调节的多元对齐模型以解决用户偏好捕捉问题 reinforcement learning RLHF large language model
30 REX-RAG: Reasoning Exploration with Policy Correction in Retrieval-Augmented Generation 提出REX-RAG以解决推理路径无效问题 reinforcement learning policy learning large language model ✅
31 Enhancing Small LLM Alignment through Margin-Based Objective Modifications under Resource Constraints 提出轻量级DPO变体以提升小型LLM对齐能力 DPO large language model
32 From Trial-and-Error to Improvement: A Systematic Analysis of LLM Exploration Mechanisms in RLVR 系统分析RLVR中LLM探索机制以提升推理能力 reinforcement learning large language model

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#题目一句话要点标签🔗⭐
33 Large Language Models for Subjective Language Understanding: A Survey 综述大型语言模型在主观语言理解中的应用与挑战 HuMoR large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
34 SAEMark: Multi-bit LLM Watermarking with Inference-Time Scaling 提出SAEMark以解决LLM水印质量与可访问性问题 manipulation

⬅️ 返回 cs.CL 首页 · 🏠 返回主页