cs.CL（2026-08-10）

📊 共 27 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) (22 🔗4) 支柱二：RL算法与架构 (RL & Architecture) (4) 支柱七：动作重定向 (Motion Retargeting) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (22 篇)

#题目一句话要点标签🔗⭐
1 UNSPECIFIC: General Constraint Synthesis for Breaking Copy-and-Paste Shortcut in LLM Instruction Following 提出UNSPECIFIC框架以解决LLM指令遵循中的复制粘贴问题 large language model instruction following ✅
2 From Values to Benchmarks: Evaluating Large Language Models for Governmental Use in Dutch 提出'Grip on LLMs'框架以评估荷兰政府用大型语言模型 large language model
3 Fusion Training for Mathematical Generalization in Large Language Models 提出思维模式融合以提升大语言模型的数学推理能力 large language model ✅
4 How Do Large Language Models Judge Social Attraction? Evidence from Theory-Grounded Persona Ratings Across Multiple LLMs and Humans 探讨大型语言模型如何评估社会吸引力 large language model
5 ELBench: A Multi-Dimensional Benchmark for Education-Facing Large Language Models 提出ELBench以评估教育领域大语言模型的多维需求 large language model
6 How Far Do Foundation Models Transfer to Infant Signals? A Cross-Dataset Transfer Audit with a Unified Need Ontology 提出跨数据集转移审计方法以解决婴儿哭声信号分析问题 foundation model
7 Pragmatic Attack Surface: Vulnerabilities of Implicit Context in Large Language Models 提出实用攻击面以解决大语言模型隐式上下文脆弱性问题 large language model
8 Subjective Multi-Bias Detection with Large Language Models 提出主观多偏见检测方法以解决文本偏见问题 large language model ✅
9 LexKairos: Benchmarking Legal Temporal Capabilities in LLMs 提出LexKairos以评估法律领域LLMs的时间能力 large language model chain-of-thought ✅
10 REFRAMED: Towards Realistic Audio Description Generation for Movies 提出REFRAMED以解决电影音频描述生成的挑战 multimodal
11 Consilience for Verifier-Free Test-Time Scaling 提出Consilience框架以解决现有VF-TTS方法的局限性 large language model
12 Verifiably grounded machine interpretation of lunar geology 提出多模态视觉语言架构以实现月球地质的自动化解读 multimodal
13 TCS-BENCH: Benchmarking State-of-the-Art Generative AI Theoretical Computer Science Research Ability 提出TCS-Bench以评估生成AI在理论计算机科学研究中的能力 large language model
14 Build it, Break it, Repeat: Benchmarking and improving LLM-manipulated disinformation detection in social media posts 提出BiBiR框架以提升社交媒体虚假信息检测能力 large language model
15 How Can Rhetoric Reward-Hack AI Reviewers? Dissecting Rhetorical Sensitivity in AI-Based Peer Review 探讨修辞选择如何影响AI评审判断以应对奖励黑客问题 large language model
16 Decoding-Level Taboo: A Diagnostic Stress Test for LLM Robustness 提出Decoding-Level Taboo以解决LLM鲁棒性评估问题 large language model
17 PragMatch: Separating Pragmatic Incongruity from Cross-Modal Mismatch in Large Vision-Language Models 提出PragMatch以解决多模态讽刺检测中的实用不一致性问题 multimodal
18 MDB-Link: Hierarchical Schema Linking for Multi-Database Text-to-SQL 提出MDB-Link以解决多数据库文本到SQL查询问题 large language model
19 Mawqif-v2: An Arabic Benchmark Dataset for Cross-Target Stance Detection 提出Mawqif-v2数据集以解决阿拉伯语跨目标立场检测问题 large language model
20 EmoS: A Theory-Grounded Framework for Evaluating and Aligning Emotional Intelligence in Spoken Language Models 提出EmoS框架以评估和提升语言模型的情感智能 instruction following
21 Evo-Bench: Can Language Models Improve Agent Harness? 提出Evo-Bench以评估智能体自我优化能力 large language model
22 Measuring the Tokenization Premium: A Cost Audit for Underserved Language Communities 提出Tokenization Equity Audit以解决语言社区的公平性问题 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🔗⭐
23 Learning Preference Adaptation for Large Language Model Personalization via Verbal Reinforcement Learning 提出AlignXada以解决LLM个性化中的任务特定偏好适应问题 reinforcement learning large language model
24 An Agentic Generative Large Language Model for Treatment Planning of Colorectal Cancer 提出GatorOnco以解决结直肠癌治疗规划中的复杂推理问题 reinforcement learning large language model
25 Se-DPO: Self-Evolving Token Credit for Direct Preference Optimization 提出Se-DPO以解决直接偏好优化中的静态令牌信用问题 DPO direct preference optimization
26 ZetaGPT: A Reference Implementation of Positional--Encoding--Free State--Space--Attention Language Models 提出ZetaGPT以解决自注意力模型中的位置编码问题 reinforcement learning RLHF chain-of-thought

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#题目一句话要点标签🔗⭐
27 Bridging the Gap Between Semantics and Reconstruction:Unifying Sign Language Translation and Production 提出Uni-SLTP以统一手语翻译与生成问题 motion reconstruction

⬅️ 返回 cs.CL 首页 · 🏠 返回主页