cs.CL（2025-02-12）

📊 共 36 篇论文 | 🔗 6 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (32 🔗5) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱一：机器人控制 (Robot Control) (1) 支柱八：物理动画 (Physics-based Animation) (1 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (32 篇)

#题目一句话要点标签🔗⭐
1 Ask in Any Modality: A Comprehensive Survey on Multimodal Retrieval-Augmented Generation 提出多模态检索增强生成方法以解决LLMs的知识过时问题 large language model multimodal ✅
2 Mitigating Hallucinations in Multimodal Spatial Relations through Constraint-Aware Prompting 提出约束感知提示框架，缓解多模态空间关系中的幻觉问题 multimodal
3 Enhancing Auto-regressive Chain-of-Thought through Loop-Aligned Reasoning 提出RELAY，通过循环对齐推理增强自回归链式思考能力 chain-of-thought ✅
4 The Science of Evaluating Foundation Models 构建评估框架以应对大型模型在多样化应用中的挑战 foundation model
5 Exploring the Potential of Large Language Models to Simulate Personality 探索大型语言模型在模拟人格特质方面的潜力，并构建相关数据集。 large language model
6 Cancer Vaccine Adjuvant Name Recognition from Biomedical Literature using Large Language Models 利用大型语言模型从生物医学文献中识别癌症疫苗佐剂名称 large language model
7 GCoT: Chain-of-Thought Prompt Learning for Graphs 提出GCoT：一种面向图数据的链式思考提示学习框架，无需文本信息。 chain-of-thought
8 A Systematic Review on the Evaluation of Large Language Models in Theory of Mind Tasks 系统性评测大型语言模型在心理理论任务中的表现 large language model
9 Systematic Knowledge Injection into Large Language Models via Diverse Augmentation for Domain-Specific RAG 提出基于多样化增强的知识注入方法，提升领域RAG中LLM的性能。 large language model
10 Data Augmentation to Improve Large Language Models in Food Hazard and Product Detection 利用ChatGPT-4o-mini数据增强提升LLM在食品危害与产品检测中的性能 large language model ✅
11 Contextual Compression Encoding for Large Language Models: A Novel Framework for Multi-Layered Parameter Space Pruning 提出上下文压缩编码(CCE)框架，用于多层参数空间剪枝，提升大语言模型部署效率。 large language model
12 Word Synchronization Challenge: A Benchmark for Word Association Responses for Large Language Models 提出词语同步挑战：用于评估大语言模型词语联想能力的基准测试 large language model
13 Redefining Simplicity: Benchmarking Large Language Models from Lexical to Document Simplification 全面评测大型语言模型在词汇、句法、句子和文档简化任务中的性能表现 large language model
14 Selective Self-to-Supervised Fine-Tuning for Generalization in Large Language Models 提出选择性自监督微调S3FT，提升大语言模型泛化能力并避免过拟合。 large language model
15 Contextual Subspace Manifold Projection for Structural Refinement of Large Language Model Representations 提出上下文子空间流形投影，用于结构化优化大语言模型表征。 large language model
16 Stop Overvaluing Multi-Agent Debate -- We Must Rethink Evaluation and Embrace Model Heterogeneity 重新评估多智能体辩论：强调异构模型，改进评测体系 large language model chain-of-thought
17 No Need for Explanations: LLMs can implicitly learn from mistakes in-context LLM可从错误中隐式学习：无需显式解释即可提升数学推理能力 large language model chain-of-thought
18 Salamandra Technical Report 发布Salamandra：多语种开源解码器大型语言模型，提供2B、7B和40B三种规模。 large language model multimodal
19 Universal Model Routing for Efficient LLM Inference UniRoute：为高效LLM推理提出通用模型路由方法，支持动态新增LLM large language model
20 A New Query Expansion Approach via Agent-Mediated Dialogic Inquiry 提出AMD框架，通过多智能体对话式探究提升查询扩展效果 large language model
21 From Haystack to Needle: Label Space Reduction for Zero-shot Classification 提出标签空间缩减方法以提升零样本分类性能 large language model
22 Measuring Diversity in Synthetic Datasets 提出DCScore，从分类角度评估合成数据集多样性，提升模型鲁棒性。 large language model ✅
23 HuDEx: Integrating Hallucination Detection and Explainability for Enhancing the Reliability of LLM responses 提出HuDEx模型，融合幻觉检测与可解释性，提升LLM响应可靠性 large language model
24 Break the Checkbox: Challenging Closed-Style Evaluations of Cultural Alignment in LLMs 挑战LLM文化价值观对齐的封闭式评估，提出更开放灵活的评估框架 large language model
25 AI for Scaling Legal Reform: Mapping and Redacting Racial Covenants in Santa Clara County 利用AI加速法律改革：在圣克拉拉县进行种族契约的识别与编辑 large language model
26 IHEval: Evaluating Language Models on Following the Instruction Hierarchy IHEval：提出指令层级评估基准，衡量语言模型在指令冲突下的表现 instruction following
27 Examining Multilingual Embedding Models Cross-Lingually Through LLM-Generated Adversarial Examples 提出CLSD评估方法，利用LLM生成对抗样本，更有效地评估跨语言语义搜索模型。 large language model ✅
28 Faithful, Unfaithful or Ambiguous? Multi-Agent Debate with Initial Stance for Summary Evaluation 提出基于多智能体辩论的摘要忠实度评估方法，并引入歧义性维度。 large language model
29 Explanation based In-Context Demonstrations Retrieval for Multilingual Grammatical Error Correction 提出基于语法错误解释的上下文示例检索方法，提升多语言语法纠错性能 large language model
30 IssueBench: Millions of Realistic Prompts for Measuring Issue Bias in LLM Writing Assistance IssueBench：构建大规模真实提示数据集，用于评估LLM写作辅助中的议题偏见 large language model
31 MultiProSE: A Multi-label Arabic Dataset for Propaganda, Sentiment, and Emotion Detection 构建多标签阿拉伯语数据集MultiProSE，用于宣传、情感和情绪检测 large language model
32 ParetoRAG: Leveraging Sentence-Context Attention for Robust and Efficient Retrieval-Augmented Generation ParetoRAG：利用句子-上下文注意力提升检索增强生成系统的鲁棒性和效率 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#题目一句话要点标签🔗⭐
33 Lexical Manifold Reconfiguration in Large Language Models: A Novel Architectural Approach for Contextual Modulation 提出基于流形重构的词汇动态调整方法，提升大语言模型上下文连贯性。 representation learning large language model
34 Fino1: On the Transferability of Reasoning-Enhanced LLMs and Reinforcement Learning to Finance 提出Fin-o1：通过金融CoT语料和强化学习提升LLM在金融领域的推理能力 reinforcement learning PPO DPO

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
35 Enhancing LLM Character-Level Manipulation via Divide and Conquer 提出基于分治策略的字符级操作方法，提升LLM在文本处理任务中的性能 manipulation large language model

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
36 DiMA: An LLM-Powered Ride-Hailing Assistant at DiDi DiMA：滴滴出行中基于LLM的出行助理，提供时空感知的对话式服务。 spatiotemporal ✅

⬅️ 返回 cs.CL 首页 · 🏠 返回主页