cs.CL（2026-08-06）

📊 共 21 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) (14 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (7 🔗2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (14 篇)

#题目一句话要点标签🔗⭐
1 Human-Like Anaphor Resolution in Large Language Models 探讨大语言模型中的人类式指代解析机制 large language model
2 MoCA: Implicit Social Context Analysis 提出MoCA框架以解决隐式社会语境分析问题 large language model multimodal
3 FormBharo: Designing and Evaluating a Voice Agent for Conversational Form Filling in Rural India 提出FormBharo以解决印度农村地区表单填写困难问题 large language model
4 MACRO: Markov Chain Routing of Transformer Layers 提出MACRO以优化Transformer层的动态路由问题 large language model ✅
5 Once a Response, Always a Response: Detecting LLM-generated Text via Latent Prompt Restoration 提出EchoPrompt以解决LLM生成文本检测问题 large language model
6 Relay, Don't Route: Adaptive Population Handoff for Cost-Efficient LLM-Driven Evolution 提出自适应种群交接以提高LLM驱动进化的成本效率 large language model
7 SkillZip: Contract-Preserving Graph Compression for Scalable Agent Skill Libraries 提出SkillZip以解决技能库压缩与执行问题 large language model
8 Training-Free Token-Level Steering for LLM Personalized Co-Writing 提出SteerWrite以解决LLM个性化协作问题 large language model
9 LangChoiceBench: Measuring and Explaining Programming-Language Choice in LLMs 提出LangChoiceBench以系统性测量LLMs的编程语言选择 large language model
10 Decomposed Entailment for Factuality Checking and Hallucination Detection 提出HallDetect以解决大型语言模型的事实性检查与幻觉检测问题 large language model
11 Mitigating Scoring Bias in LLM-as-a-Judge via Random Number Generation 提出随机数生成方法以解决LLM评分偏差问题 large language model
12 Where Models Converge and Humans Diverge: A Coverage Framework for Distributional Pluralism in Open-Ended Generation 提出人类基础框架以衡量LLM生成内容的分布广度 large language model
13 MoCA: Implicit Social Context Analysis 提出MoCA框架以解决隐性社会语境分析问题 large language model multimodal
14 Beyond "AI Language": The case for the idiolectal nature of LLM output 提出LLM输出的个体化特征以解决AI语言分析问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (7 篇)

#题目一句话要点标签🔗⭐
15 M$^3$R-Bench: A Unified Benchmark for Evidence-Grounded Multimodal Metaphor Understanding 提出M$^3$R-Bench以解决多模态隐喻理解中的证据不足问题 reinforcement learning multimodal ✅
16 RP-OPSD: Reasoning-Pivot-Guided On-Policy Self-Distillation for Multilingual Reasoning Transfer 提出RP-OPSD以解决多语言推理迁移问题 distillation large language model ✅
17 On-Policy Delta Distillation for Multilingual Math Reasoning 提出On-Policy Delta Distillation以提升多语言数学推理能力 reinforcement learning distillation
18 Task-Conditional Flow Matching for Balanced Multilingual Text Embedding Adaptation 提出任务条件流匹配以解决多语言文本嵌入适应问题 flow matching
19 Enhancing Social Intelligence in LLMs with Hierarchical Reasoning and Utterance-Level Goal Rewarding 提出TSR框架与LHRL-VGR算法以提升LLMs的社交智能 reinforcement learning large language model
20 Learning When to Trust via Selective Context Preference Optimization 提出SCOPE以解决语言模型的选择性信任问题 DPO direct preference optimization
21 GRASP: Reinforcing Language Model Anonymizers with Group Relative Policy Optimization 提出GRASP以强化语言模型匿名化技术 DPO direct preference optimization large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页