cs.CL（2026-09-16）

📊 共 19 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (14) 支柱二：RL算法与架构 (RL & Architecture) (5 🔗1)

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

#题目一句话要点标签🔗⭐
1 Attention Dispersion as a Diagnostic Signal for Hallucination in Large Language Models 提出注意力分散作为大型语言模型幻觉诊断信号 large language model
2 From a River in Gilead to the Inference Distributions of Large Language Models: Covert Dialect Bias and Linguistic Profiling at Scale 提出隐性方言偏见分析方法以解决住房筛选中的语言歧视问题 large language model
3 Divide and Conquer: Mixture-of-Bottleneck Experts in Informative Ordinal Space for Video-based Multimodal Sentiment Analysis 提出混合瓶颈专家框架以解决视频多模态情感分析问题 multimodal
4 Emotion Experience, Expression, and Perception: Emotion Analysis on Multimodal Social Media Posts 提出Mult2EMo数据集以解决社交媒体情感重构问题 multimodal
5 Rollback the World, Keep the Reflection: Rollback-Induced Reflection for Long-Horizon LLM Agents 提出回滚诱导反思框架以解决长时间任务中的错误累积问题 large language model
6 ReFigBench: Benchmarking Scientific Figure Reconstruction as Editable PowerPoint Artifacts 提出ReFigBench以解决科学图形重建的可编辑性问题 multimodal
7 Zero-Shot Cross-Lingual Recognition of Sign Language Handshapes 提出零-shot跨语言手势识别框架以解决低资源手语问题 zero-shot transfer
8 A Zeroth-Order Paradigm for LLM Preference Alignment 提出Comparison-based Preference Optimization以解决LLM偏好对齐问题 large language model
9 Monitoring and Discovering Reward Hacking with Internal Representations during LLM Evaluations 提出内部表示监测方法以发现大语言模型中的奖励黑客行为 chain-of-thought
10 A Calibrated Instrument for Measuring How Inference Optimizations Affect Output Quality 提出一种校准工具以测量推理优化对输出质量的影响 large language model
11 A Scalable Framework for Automated NER Annotation Correction in Low-Resource Languages 提出多步骤框架以提升低资源语言NER注释质量 large language model
12 Beyond Accuracy: How Procedural Traces Shift the Decision Criterion of LLM Overseers 提出程序性追踪以改善大型语言模型监督决策标准 large language model
13 Linguistic Triggers of Gender and Racial Bias in Open-Weight LLMs Applied to Recruitment 提出多模型审计方法以识别招聘中的性别与种族偏见 large language model
14 TeochewBench: A Human-Reviewed Benchmark for Teochew Hanzi Translation 提出TeochewBench以评估潮州汉字翻译模型的性能 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🔗⭐
15 Size Matters: Foundation Model for Czech HTML documents 提出HTML-LM以解决捷克HTML文档处理效率问题 distillation large language model foundation model ✅
16 DualSQL: Text-to-SQL with Multi-Agent Reinforcement Learning 提出DualSQL以解决Text-to-SQL系统中的任务协同问题 reinforcement learning
17 STRETCH the Boundaries: A Unified Self-Taught Framework for Progressive LLM Evolution 提出STRETCH框架以解决大语言模型能力停滞问题 reinforcement learning large language model
18 SEA-LION-v4.8: A Technical Report 提出Nemotron-SEA-LION-v4.8以提升东南亚语言处理能力 distillation instruction following
19 G-Mamba: Sparse Graph-Guided Mamba for Audio-Visual Speech Enhancement 提出SG-Mamba以解决音视频语音增强中的效率与准确性问题 Mamba

⬅️ 返回 cs.CL 首页 · 🏠 返回主页