cs.CL（2026-10-20）

📊 共 34 篇论文 | 🔗 6 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (28 🔗4) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗2) 支柱一：机器人控制 (Robot Control) (1) 支柱三：空间感知与语义 (Perception & Semantics) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (28 篇)

#题目一句话要点标签🔗⭐
1 BitMTP: When Multi-Token Prediction Meets Low-Bit Large Language Models 提出BitMTP以解决低比特大语言模型的多标记预测问题 large language model ✅
2 Learned Readout Tokens for Extracting Large Language Model Confidence 提出ScratchProbe以提升大语言模型输出置信度评估 large language model
3 ABench: Adversarily Benchmarking Large Language Models across Taxonomized Values 提出ABench以解决大型语言模型文化价值对齐问题 large language model
4 AudiPsy: Evidence-Grounded Multimodal Reasoning over Spoken Counseling Conversations for Depression Assessment 提出AudiPsy以解决抑郁评估中的多模态推理问题 multimodal
5 NarraSpace: Multimodal Scene-Grounded Evidence for Picture-Description Dementia Classification 提出NarraSpace以解决图像描述性痴呆分类问题 multimodal
6 Speak vs. Know: Balancing Behavior and Knowledge Distributions of Large Language Models 提出可学习的分布组合以解决LLM行为与知识不匹配问题 large language model
7 TeCoP: Accelerating Diffusion Large Language Model Decoding via Tentative Context Pipelining 提出TeCoP以加速扩散大语言模型解码过程 large language model
8 Detecting Errors in Large Language Model Responses: The Incremental Predictive Value of Hidden States 通过整合隐藏状态提升大语言模型响应错误检测能力 large language model
9 Africa-Papers: A 10-Billion-Token Multi-Domain Academic Corpus for African Foundation Language Models 提出Africa-Papers以解决非洲学术资源匮乏问题 large language model foundation model
10 Disclosure Begets Disclosure: A Self-Reinforcing Privacy Loop in LLM Agents with Persistent Memory 提出自我强化隐私循环以解决LLM代理的隐私泄露问题 large language model
11 From Tokens to Files: Multi-Granularity Detection and Localization of AI-Involved Code 提出多粒度检测与定位方法以区分AI参与的代码 large language model
12 Benchmarking Arabic Dialects for Math Problems 提出DAR-MGSM基准以评估阿拉伯方言数学推理能力 large language model
13 Large Flow Language Models 提出Lafa以解决大规模流语言模型训练效率问题 instruction following
14 Every Model Leaves a Trace: Multi-Resolution LLM Fingerprinting 提出多分辨率LLM指纹技术以区分模型身份 large language model
15 Beyond a Single Sentiment Score: Topical and Affective Dimensions of Emoji Meaning on Twitter 提出多维度表情符号分析方法以解决情感评分不足问题 multimodal
16 Temporal Evidence-Parameter Co-Alignment for LLM Reasoning over Temporal Knowledge Graphs 提出TEPCA框架以解决LLM在时间知识图谱推理中的不足 large language model
17 BAIT: Can LLMs Find What Biases a Reader? A Benchmark for Cognitive Bias Triggers in News 提出BAIT以识别新闻中的认知偏见触发因素 large language model
18 CollabSciReM: Aligning Language Models for Scientific Conversations via Science-Aware Reward Decomposition 提出CollabSciReM以解决科学对话中的模型对齐问题 large language model
19 Hearsay or Fact? How Framing and Elicitation Shape LLM Probability Updates 研究大型语言模型在信息更新中的概率变化机制 large language model ✅
20 Beyond Calibration: Temporal LLM Confidence Assessment Across Languages and Local Settings 提出跨语言和本地设置的时序LLM信心评估方法 large language model
21 Cache Engineering for Agents 提出缓存工程方案以优化大语言模型代理的任务处理 large language model ✅
22 From Abstraction to Action: DSLs for Natural Language Abstraction Interpretation and Execution 提出领域特定语言以解决自然语言抽象指令解析问题 instruction following
23 Reading Too Much Into It? Interpretive Preferences and Commitment in LLM Mentalisation under Ambiguity 提出MentalLoom以解决LLM在模糊社交情境中的解释偏好问题 large language model
24 From DQI to C-DQI: Automatic Codebook Generation and Evaluation for Measuring Computational Discourse Quality Index 提出基于LLM的代码本生成与评估方法以提升议会话语质量评估 large language model
25 Why Do LLMs Accept Generics? Explaining Acceptability using Psycholinguistic and Model-Derived Factors 探讨大型语言模型如何接受泛化陈述的心理语言学因素 large language model
26 Are Linguistic and Arithmetic Circuits Dissociated in LLMs? 探讨大语言模型中语言与算术电路的分离性 large language model
27 Tracing Recurrent and Emergent Hallucination Patterns in Decomposed Text-to-SQL Generation 提出逐步评估框架以解决Text-to-SQL生成中的幻觉问题 large language model ✅
28 Why Static Probes Fail: Context Determines Deception Feature Composition 提出多维子空间方法以解决静态探测器在欺骗检测中的局限性 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
29 Reward Misspecification Degrades Chain-of-Thought Monitorability 提出奖励误指定以解决链式思维监控问题 reinforcement learning chain-of-thought ✅
30 On-Policy Transition Distillation 提出On-Policy Transition Distillation以提升蒸馏学习效果 distillation instruction following
31 Capable Teacher, Myopic Scorer: Reward-Free Teacher Repair for Agentic On-Policy Distillation 提出R2S方法以解决Agentic OPD中的评分误差问题 teacher-student distillation ✅
32 PAR: Progress-Aligned Recurrence for Length Generalization in State Tracking 提出进度对齐递归方法以解决状态跟踪中的长度泛化问题 distillation chain-of-thought

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
33 Testing Associative Creativity in Humans and Multimodal LLMs with Difficult-to-Name Visual Stimuli 研究多模态大语言模型在抽象视觉刺激下的联想创造力 manipulation large language model multimodal

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗⭐
34 PhonoBridge: Error-Aware Phoneme-Mediated EMG-to-Text Reconstruction 提出PhonoBridge以解决EMG文本重建中的噪声问题 open-vocabulary open vocabulary large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页