cs.CL（2026-07-21）

📊 共 16 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) (9 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (5 🔗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) (9 篇)

#题目一句话要点标签🔗⭐
1 MeetingToM: Evaluating Multimodal LLMs on Theory-of-Mind Reasoning in Multi-Party Meetings 提出MeetingToM以解决多方会议中的心智理论推理问题 large language model multimodal
2 Prompt Design at Scale: How Format, Instruction Count, and Context Length Shape Instruction Adherence and Hallucination in Large Language Models 提出大规模提示设计方法以优化指令遵循与模型记忆 large language model instruction following ✅
3 CASE: Causal Alignment and Structural Enforcement for Improving Chain-of-Thought Faithfulness 提出CASE框架以解决链式推理的忠实性问题 large language model chain-of-thought ✅
4 Stochastic Meta-Unlearning: Bridging Language Backbone and Multimodal Unlearning 提出随机元遗忘以解决多模态模型的遗忘问题 multimodal
5 Find Before You Fine-Tune: A Diagnostic Study of Small LLMs for Cybersecurity QA 提出FiT框架以优化小型LLM在网络安全问答中的应用 large language model instruction following
6 DAIS: Dependency-Aware Intermediate QA Supervision for Complex Reasoning 提出依赖感知中间问答监督以解决复杂推理问题 chain-of-thought
7 AutoJourn: Multi-Perspective Summarisation, Bias Detection and Bias Neutralisation for LLM-Generated News in Automated Journalism 提出AutoJourn以解决自动化新闻中的多视角生成与偏见检测问题 large language model
8 Two-Level Meta-Rubrics for Evaluating Open-Ended Generation: GAMUT, a Benchmark for Factual Completeness 提出双层元评分标准以评估开放式生成的事实完整性 multimodal
9 Reasoning Error from Known Fact: Step-Level Self-Consistency Group Relative Policy Optimization for LLM 提出SSC-GRPO以解决LLM推理中的幻觉问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#题目一句话要点标签🔗⭐
10 Rationale-Guided Knowledge Distillation for Cross-Lingual Stance Detection 提出基于推理引导的知识蒸馏方法以解决跨语言立场检测问题 contrastive learning distillation large language model
11 Copy Less, Ground More: Overcoming Repetitive Copying in Long-Context Reasoning via Evidence-Aware Reinforcement Learning 提出GEAR以解决长上下文推理中的重复复制问题 reinforcement learning reward shaping large language model
12 The Price of Reasoning: Cost-Quality Tradeoffs in Reinforcement Learning for Neural Machine Translation 提出基于可验证奖励的强化学习方法以提升神经机器翻译质量 reinforcement learning large language model
13 Beyond Score Prediction: LLM-Based Essay Scoring and Feedback Generation via Reinforcement Learning with Rubric Rewards 提出RLAES框架以解决自动化作文评分与反馈生成问题 reinforcement learning large language model ✅
14 RF-Agent: A Practical Framework for Building Language Agents for RFIC Design 提出RF-Agent框架以解决RF电路设计中的数据稀缺问题 distillation 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🔗⭐
15 Computational Humor with Multimodal LLMs: Methods, Datasets, Evaluation, and Challenges 提出多模态大语言模型以解决幽默理解与生成问题 HuMoR multimodal

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
16 Inference-Time Steering for Cross-Lingual Factual Consistency in LLMs 提出推理时间引导以解决跨语言事实一致性问题 manipulation DPO direct preference optimization

⬅️ 返回 cs.CL 首页 · 🏠 返回主页