cs.CL（2026-01-14）

📊 共 23 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) (19 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (19 篇)

#题目一句话要点标签🔗⭐
1 SLAM-LLM: A Modular, Open-Source Multimodal Large Language Model Framework and Best Practice for Speech, Language, Audio and Music Processing SLAM-LLM：一个模块化、开源的多模态大语言模型框架，专注于语音、语言、音频和音乐处理 large language model multimodal
2 Benchmarking Post-Training Quantization of Large Language Models under Microscaling Floating Point Formats 系统评估微缩浮点格式下大语言模型后训练量化方法，并提供实用指导。 large language model multimodal
3 From Symbolic to Natural-Language Relations: Rethinking Knowledge Graph Construction in the Era of Large Language Models 提出自然语言关系描述以改进知识图谱构建 large language model
4 The Imperfective Paradox in Large Language Models 提出ImperfectiveNLI数据集以解决LLMs的语义理解问题 large language model
5 LLMs can Compress LLMs: Adaptive Pruning by Agents 提出Agent引导的自适应剪枝方法，利用LLM压缩LLM，提升知识保留率。 large language model foundation model
6 LLMs Got Rhythm? Hybrid Phonological Filtering for Greek Poetry Rhyme Detection and Generation 提出混合音韵过滤系统，提升LLM在希腊诗歌押韵检测与生成任务上的性能 large language model chain-of-thought
7 MCGA: A Multi-task Classical Chinese Literary Genre Audio Corpus 提出MCGA：一个面向多任务的古文音频语料库，促进多模态大模型在古文研究中的应用。 large language model multimodal ✅
8 OrthoGeoLoRA: Geometric Parameter-Efficient Fine-Tuning for Structured Social Science Concept Retrieval on theWeb OrthoGeoLoRA：用于Web端社会科学概念检索的几何参数高效微调方法 large language model foundation model
9 Routing with Generated Data: Annotation-Free LLM Skill Estimation and Expert Selection 提出RGD设定与CASCAL路由，解决无标注数据下LLM专家模型动态选择问题 large language model
10 Ability Transfer and Recovery via Modularized Parameters Localization 提出ACT：通过模块化参数定位实现大模型能力迁移与恢复 large language model
11 Improving Symbolic Translation of Language Models for Logical Reasoning 针对逻辑推理，提出改进语言模型符号翻译的方法，提升小模型的推理能力。 large language model
12 ProFit: Leveraging High-Value Signals in SFT via Probability-Guided Token Selection ProFit：通过概率引导的token选择，提升SFT中高价值信号的利用率 large language model
13 SubTokenTest: A Practical Benchmark for Real-World Sub-token Understanding SubTokenTest：一个评估LLM在现实场景中子词理解能力的实用基准测试。 large language model
14 SlidesGen-Bench: Evaluating Slides Generation via Computational and Quantitative Metrics 提出SlidesGen-Bench，通过可计算指标评估幻灯片生成质量，解决现有评估方法的主观性和不可比性问题。 large language model ✅
15 Dissecting Judicial Reasoning in U.S. Copyright Damage Awards 提出一种基于篇章结构的LLM方法，用于解析美国版权损害赔偿判决中的司法推理。 large language model
16 Structured Knowledge Representation through Contextual Pages for Retrieval-Augmented Generation 提出PAGER框架，通过上下文页面结构化知识表示增强检索增强生成效果 large language model ✅
17 When to Trust: A Causality-Aware Calibration Framework for Accurate Knowledge Graph Retrieval-Augmented Generation 提出Ca2KG框架，解决KG-RAG中知识不完备导致的过度自信问题。 large language model
18 Identity-Robust Language Model Generation via Content Integrity Preservation 提出内容完整性保持的身份鲁棒语言模型生成框架，减少身份偏见。 large language model
19 Contrastive Bi-Encoder Models for Multi-Label Skill Extraction: Enhancing ESCO Ontology Matching with BERT and Attention Mechanisms 提出基于对比学习的双编码器模型，用于增强ESCO本体匹配的多标签技能抽取。 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
20 DPWriter: Reinforcement Learning with Diverse Planning Branching for Creative Writing DPWriter：通过多样化规划分支的强化学习方法提升创意写作中LLM的输出多样性。 reinforcement learning large language model chain-of-thought
21 Relation Extraction Capabilities of LLMs on Clinical Text: A Bilingual Evaluation for English and Turkish 提出Relation-Aware Retrieval，用于提升LLM在临床文本关系抽取中的性能，并构建了英土双语数据集。 contrastive learning large language model chain-of-thought
22 Mi:dm 2.0 Korea-centric Bilingual Language Models Mi:dm 2.0：面向韩国的双语大语言模型，提升文化理解和性能 curriculum learning large language model ✅

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
23 UserLM-R1: Modeling Human Reasoning in User Language Models with Multi-Reward Reinforcement Learning UserLM-R1：利用多奖励强化学习建模用户语言模型中的人类推理 manipulation reinforcement learning

⬅️ 返回 cs.CL 首页 · 🏠 返回主页