cs.CL（2026-07-22）

📊 共 16 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 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (6)

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

#题目一句话要点标签🔗⭐
1 Sound Probabilistic Safety Bounds for Large Language Models 提出一种新框架以计算大型语言模型的安全概率界限 large language model
2 LKValues: Aligning Large Language Models with Sri Lankan Societal Values 提出LKValues以解决斯里兰卡社会价值对齐问题 large language model ✅
3 PyroDash: Cost-Efficient Token-Level Small-Large Language Model Collaborative Inference 提出PyroDash以实现小型与大型语言模型的协同推理 large language model
4 D2VBench: Benchmarking Large Language Models with Value Dilemmas in Daily Scenarios 提出D2VBench以解决大语言模型价值对齐评估问题 large language model ✅
5 VizRAG: Enhancing Retrieval-Augmented Generation with Hypergraph Visualization 提出VizRAG以解决传统RAG系统的视觉感知不足问题 large language model multimodal
6 Which Values Do LLMs Confuse? A Schwartz-Based Recognition Study 提出基于施瓦茨价值观的识别研究以评估大型语言模型的价值混淆 large language model
7 surprisal is Not a Theory 批判性分析大语言模型中的惊讶理论应用 large language model
8 Gotta Catch them all: the modes of Sycophancy 提出多模式的谄媚行为分析以提高语言模型的准确性 large language model
9 Understanding the Impact of Linguistic Realization Choices on LLM Stance with Causal Tracing 研究语言构造选择对大型语言模型立场的影响 large language model
10 Beyond Relevance-Centric Retrieval: Rubric-Oriented Document Set Selection and Ranking 提出Rubric4Setwise以解决文档集选择与排序问题 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🔗⭐
11 Reinforcement Learning for Large Language Model Selective Evidence Adoption from Contaminated Retrieval Results 提出SelectBench以解决大语言模型选择性证据采纳问题 reinforcement learning reward shaping large language model
12 SLPO: Scaling Latent Reasoning via a Surrogate Policy 提出SLPO以解决潜在推理中的奖励优化问题 reinforcement learning chain-of-thought
13 When Does Knowledge Distillation Hurt? Reliability-Aware Distillation for Low-Resource Language Summarization 提出可靠性感知蒸馏方法以解决低资源语言摘要问题 distillation
14 Notes to Self: Can LLMs Benefit from Experiential Abstractions? 提出经验抽象方法以提升大型语言模型的推理能力 reinforcement learning large language model
15 Multi-Mask Diffusion Language Models for Few-Step Generation 提出多掩码扩散语言模型以解决少步生成问题 distillation MDM
16 Solar Open 2 Technical Report 提出Solar Open 2以解决长时间跨度智能任务的挑战 linear attention distillation

⬅️ 返回 cs.CL 首页 · 🏠 返回主页