cs.CL（2025-11-07）

📊 共 25 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) (20 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (4) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (20 篇)

#题目一句话要点标签🔗⭐
1 A multimodal multiplex of the mental lexicon for multilingual individuals 提出多模态多层心理词汇模型，研究多语者词汇组织及视觉输入影响 multimodal
2 Multi-Scale Feature Fusion and Graph Neural Network Integration for Text Classification with Large Language Models 提出融合多尺度特征、图神经网络与大语言模型的文本分类方法 large language model
3 Large Language Models for Explainable Threat Intelligence RAGRecon：利用大语言模型和知识图谱实现可解释的威胁情报分析 large language model
4 Acquiring Common Chinese Emotional Events Using Large Language Model 利用大型语言模型获取通用中文情感事件知识库，提升情感分析效果 large language model
5 LoPT: Lossless Parallel Tokenization Acceleration for Long Context Inference of Large Language Model LoPT：面向大语言模型长文本推理的无损并行分词加速框架 large language model
6 Motif 2 12.7B technical report Motif-2-12.7B：结合架构创新与系统优化，提升大语言模型效率前沿。 large language model foundation model
7 Optimizing Diversity and Quality through Base-Aligned Model Collaboration 提出Base-Aligned Model Collaboration (BACo)框架，在保证质量的同时提升LLM生成文本的多样性。 large language model
8 Steering Language Models with Weight Arithmetic 提出基于权重运算的语言模型引导方法，提升模型行为控制能力。 large language model
9 Language Generation and Identification From Partial Enumeration: Tight Density Bounds and Topological Characterizations 提出语言生成与识别的新框架以解决部分枚举问题 large language model
10 Evaluating LLM Understanding via Structured Tabular Decision Simulations 提出结构化表格决策模拟以评估LLM理解能力 large language model
11 Learn More, Forget Less: A Gradient-Aware Data Selection Approach for LLM 提出GrADS梯度感知数据选择方法，缓解LLM领域微调中的灾难性遗忘问题。 large language model
12 Pluralistic Behavior Suite: Stress-Testing Multi-Turn Adherence to Custom Behavioral Policies 提出PBSUITE，用于压力测试LLM在多轮对话中对自定义行为策略的遵守情况。 large language model
13 OckBench: Measuring the Efficiency of LLM Reasoning OckBench：提出兼顾准确率与token效率的大语言模型推理评估基准 large language model
14 What Are the Facts? Automated Extraction of Court-Established Facts from Criminal-Court Opinions 提出基于正则表达式和LLM的混合方法，自动提取刑事判决书中的案件事实描述。 large language model
15 UA-Code-Bench: A Competitive Programming Benchmark for Evaluating LLM Code Generation in Ukrainian 提出UA-Code-Bench乌克兰语代码生成评测基准，评估LLM在低资源语言下的编程能力 large language model ✅
16 BudgetMem: Learning Selective Memory Policies for Cost-Efficient Long-Context Processing in Language Models BudgetMem：面向资源受限场景，学习选择性记忆策略以实现高效长文本处理 large language model
17 Listening Between the Lines: Decoding Podcast Narratives with Language Modeling 提出基于BERT微调的框架标注方法，用于解码播客叙事中的潜在框架。 large language model
18 Mind the Gap... or Not? How Translation Errors and Evaluation Details Skew Multilingual Results 揭示多语言LLM数学能力评估偏差：翻译错误与答案提取影响显著 large language model
19 AgentExpt: Automating AI Experiment Design with LLM-based Resource Retrieval Agent AgentExpt：利用LLM驱动的资源检索Agent自动化AI实验设计 large language model
20 SDS KoPub VDR: A Benchmark Dataset for Visual Document Retrieval in Korean Public Documents 提出SDS KoPub VDR，用于评估韩语公共文档视觉文档检索 multimodal ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
21 Effectiveness of Chain-of-Thought in Distilling Reasoning Capability from Large Language Models 利用思维链蒸馏提升小模型在自然语言推理任务上的性能 distillation large language model chain-of-thought
22 Iterative Layer-wise Distillation for Efficient Compression of Large Language Models 提出迭代层蒸馏方法，用于高效压缩大型语言模型，在性能损失可控下显著减少模型层数。 distillation large language model
23 Reflective Personalization Optimization: A Post-hoc Rewriting Framework for Black-Box Large Language Models 提出RPO框架，解耦内容生成与个性化，提升黑盒大语言模型的用户定制能力。 reinforcement learning large language model
24 Minority-Aware Satisfaction Estimation in Dialogue Systems via Preference-Adaptive Reinforcement Learning 提出PAda-PPO框架，通过偏好自适应强化学习提升对话系统中少数群体用户满意度估计。 reinforcement learning PPO

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
25 ConVerse: Benchmarking Contextual Safety in Agent-to-Agent Conversations ConVerse：评估Agent间对话中上下文安全性的基准测试 manipulation

⬅️ 返回 cs.CL 首页 · 🏠 返回主页