cs.CL（2026-06-08）

📊 共 33 篇论文 | 🔗 7 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (27 🔗7) 支柱二：RL算法与架构 (RL & Architecture) (6)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (27 篇)

#题目一句话要点标签🔗⭐
1 H2HMem: A Multimodal Memory Benchmark for Agents in Human-Human Interactions 提出H2HMem以解决人际互动中的多模态记忆评估问题 large language model multimodal
2 PsychoSafe: Eliciting Psychologically-Informed Refusals in Large Language Models 提出PsychoSafe框架以改善大语言模型的拒绝响应 large language model
3 When Built-in Thinking Helps and Hurts: Constraint-Level Error Shifts in Instruction Following 研究思维模式对指令遵循的影响及其局限性 instruction following
4 Civil Court Simulation with Large Language Models 提出多智能体框架以模拟中国民事法庭审判 large language model ✅
5 Detecting Differences Is Not Understanding Structure: Large Language Models Fail at Graph Isomorphism 揭示大型语言模型在图同构理解中的局限性 large language model
6 In-Context Learning for the Imputation of Public Opinion Data with Large Language Models 提出基于上下文学习的缺失公共意见数据填补方法 large language model
7 Explicit Representation Alignment for Multimodal Sentiment Analysis 提出显式表示对齐方法以解决多模态情感分析中的表示不一致问题 multimodal
8 Where Does the Answer Come From? Benchmarking View-Level Visual Evidence Identification in Multi-View MLLMs for Autonomous Driving 提出多视角视觉问答基准以解决自主驾驶中的证据识别问题 large language model multimodal
9 SafeRun: Enabling Determinism in LLM Planning for Running 提出SafeRun以解决大型语言模型在规划中的确定性问题 large language model instruction following ✅
10 IS-CoT: Breaking the Long-form Generation Collapse via Interleaved Structural Thinking 提出IS-CoT框架以解决长文本生成中的崩溃问题 large language model chain-of-thought
11 Is Text All You Need? Text as a Universal Information Bottleneck for Speech LLMs 提出Convex Gate以解决语音与语言模型的融合问题 large language model multimodal
12 Code Is More Than Text: Uncertainty Estimation for Code Generation 提出代码生成中的不确定性估计方法以提高安全性 large language model
13 Unified Energy for Invariant and Independent Decoding in Diffusion Language Models 提出统一能量以解决扩散语言模型中的解码不变性与独立性问题 large language model
14 SEF-CLGC at SemEval-2026 Task 11: Logical Notation Impact on Language Model Performance 提出SEF-CLGC框架以提升语言模型推理性能 large language model
15 Cross-Modal Masking for Robust Silent Speech Synthesis Using sEMG and Lipreading 提出跨模态掩蔽以增强无声语音合成的鲁棒性 multimodal
16 Gradient-Guided Reward Optimization for Inference-time Alignment 提出梯度引导奖励优化以解决推理时对齐问题 large language model ✅
17 Interpretable Crisis Behavior Analysis Using Mobility and Social Media Data 提出统一管道以分析危机行为，整合移动与社交媒体数据 multimodal
18 MUDIDI: A Two-Stage Framework for Multilingual Dictionary Digitization with Language Models 提出MUDIDI框架以解决多语言词典数字化问题 large language model ✅
19 What Should a Skill Remember? Quality-Cost Trade-offs in Cost-Aware Skill Rewriting for Language Model Agents 提出成本感知技能重写方法以优化语言模型代理的性能 large language model ✅
20 LexRubric: A Rubric-Guided Diagnostic Benchmark for Open-Ended Legal Tasks 提出LexRubric以解决开放式法律任务评估问题 large language model ✅
21 Multi-Hop Knowledge Composition is Bound by Pretraining Exposure 提出多跳知识组合方法以解决语言模型推理不足问题 large language model
22 How Far Can Prompting Go for Minimal-Edit Ukrainian Grammatical Error Correction? 评估多种语言模型在乌克兰语语法错误纠正中的表现 large language model
23 TruthSplit: Operationalizing Conditional Validity in Arguments Through Multi-Perspective Reasoning 提出TruthSplit以解决多视角论证分析中的条件有效性问题 large language model
24 Symbolic and Abstractive Reasoning with Complex Visual Queries 提出复杂视觉查询以解决多模态大语言模型的推理挑战 large language model
25 Emergent Misalignment Can Be Induced by Sycophancy and Reversed via Alignment Gating 提出Alignment Gating以解决语言模型的紧急失调问题 large language model
26 Beyond Averages: Evaluating LLMs on Human Survey Replication at the Distributional Level 提出基于分布层面的评估方法以改进LLM对人类调查的模拟 multimodal
27 Language-Aware Token Boosting: LLM Language Confusion Reduction Without Tuning 提出无调优的语言感知令牌增强方法以减少语言混淆 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🔗⭐
28 The Neutral Mask: How RLHF Provides Shallow Alignment while Leaving Partisan Structure Intact in a Large Language Model 提出中立掩码以解决RLHF在语言模型中的偏见问题 reinforcement learning RLHF large language model
29 Emergence of Context Characteristics Sensitivity in Large Language Models 研究大型语言模型在指令微调中的上下文特征敏感性变化 reinforcement learning DPO direct preference optimization
30 Bridging the Agent-World Gap: Text World Models for LLM-based Agents 提出文本世界模型以解决LLM代理的环境理解问题 world model world models large language model
31 Multilingual Sentiment Aware Text Summarization A Reinforcement Learning Approach for Consistency Maintenance 提出情感感知的KL正则化以解决情感漂移问题 reinforcement learning RLHF large language model
32 SG-OPD: Sign-Gated On-Policy Distillation via Sign-Consistency Gating and Phased Teacher Sampling 提出SG-OPD以解决现有OPD方法的有效性问题 reinforcement learning distillation
33 Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO 提出AdvGRPO以解决语言模型的自适应红队问题 reinforcement learning PPO DPO

⬅️ 返回 cs.CL 首页 · 🏠 返回主页