cs.CL（2026-07-16）

📊 共 15 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (10 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (5 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (10 篇)

#题目一句话要点标签🔗⭐
1 Beyond the Leaderboard: Design Lessons for Trustworthy Multimodal VQA 提出多模态VQA设计原则以提升医疗AI的可信度 multimodal
2 Controlled Reformulation Testing for Logical Consistency in Large Language Models 提出CRTBench以评估大型语言模型的逻辑一致性问题 large language model
3 TikStance: A Multimodal and Hierarchical Dataset for Multi-target Stance Analysis in TikTok Political Conversations 提出TikStance数据集以解决短视频政治对话中的多目标立场分析问题 multimodal
4 OmniaBench: Benchmarking General AI Agents Across Diverse Scenarios 提出OmniaBench以解决通用AI代理评估的局限性问题 large language model
5 Show Me How You Reason and I'll Tell You Who You Are: Reasoning Graphs for Robust LLM Authorship Attribution 提出推理图方法以解决LLM作者归属问题 large language model
6 Rubrics on Trial: Evolving Rubrics from a Single Query via Synthetic Pairwise Evidence 提出Rubrics on Trial以解决查询特定评分标准构建难题 large language model
7 D-cut: Adaptive Verification Depth Pruning for Batched Speculative Decoding 提出D-Cut以解决高并发下的推理效率问题 large language model
8 Routing Ceilings Are Domain-Independent: Structural Prior Injection in Code Security Vulnerability Detection 提出结构先验以解决代码安全漏洞检测中的路由问题 large language model ✅
9 Investigating first-language bias in LLM-based automated essay scoring: A cross-prompt evaluation of an open-weight AI-model on TOEFL essays 研究L1偏见对基于LLM的自动评分影响 large language model
10 How Well Does AI-Generated Feedback Work? Intrinsic and Extrinsic Evaluation across more than 20,000 EFL Essay Drafts 评估AI生成反馈在外语写作中的有效性 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🔗⭐
11 Answer-Conditioned Chains of Thought Degrade Verifiable-Reasoning Distillation in Large Language Models 提出新方法以解决大语言模型推理蒸馏中的数据降解问题 distillation large language model
12 SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning 提出SEED框架以解决稀疏奖励下的决策监督问题 reinforcement learning policy learning distillation ✅
13 Digital Pantheon: Simulating and Auditing Coalition Formation with LLM Agents 提出多代理框架以模拟和审计政治联盟形成 reinforcement learning RLHF DPO
14 Gold-Guided Programmatic Distillation for Financial Reasoning over Hybrid Tables and Text 提出金导向程序蒸馏以解决混合表格与文本的金融推理问题 distillation large language model
15 Mask-Aware Policy Gradients for Diffusion Language Models 提出Mask-Aware策略梯度以提升MDLM的推理能力 reinforcement learning large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页