cs.CL（2025-01-16）

📊 共 17 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 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (3)

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

#题目一句话要点标签🔗⭐
1 Multiple Choice Questions: Reasoning Makes Large Language Models (LLMs) More Self-Confident Even When They Are Wrong 大语言模型在多选题中进行推理时，即使错误也更自信 large language model chain-of-thought
2 Perspective Transition of Large Language Models for Solving Subjective Tasks 提出RPT方法，通过视角转换提升大语言模型在主观任务上的表现 large language model chain-of-thought
3 Suggesting Code Edits in Interactive Machine Learning Notebooks Using Large Language Models 提出基于大型语言模型的交互式机器学习Notebook代码编辑建议方法与数据集。 large language model
4 The Heap: A Contamination-Free Multilingual Code Dataset for Evaluating Large Language Models 发布The Heap：一个无污染的多语言代码数据集，用于评估大型语言模型 large language model
5 Foundations of Large Language Models 大型语言模型基础概念解析，为NLP从业者提供参考 large language model
6 Conversational Text Extraction with Large Language Models Using Retrieval-Augmented Systems 提出基于RAG的LLM对话式文本抽取系统，提升PDF文档交互体验 large language model
7 Enhancing Lexicon-Based Text Embeddings with Large Language Models 提出基于LLM的词典嵌入LENS，提升文本嵌入性能并保持紧凑表示 large language model
8 Augmenting a Large Language Model with a Combination of Text and Visual Data for Conversational Visualization of Global Geospatial Data 提出一种结合文本和视觉数据增强LLM的全球地理空间数据会话式可视化方法 large language model
9 Delayed Fusion: Integrating Large Language Models into First-Pass Decoding in End-to-end Speech Recognition 提出延迟融合方法，解决端到端语音识别中LLM集成难题 large language model
10 Domain Adaptation of Foundation LLMs for e-Commerce 提出e-Llama，通过领域自适应提升LLM在电商领域的性能 large language model foundation model
11 OmniThink: Expanding Knowledge Boundaries in Machine Writing through Thinking OmniThink：通过模拟人类思考过程，扩展机器写作的知识边界 large language model ✅
12 A Study of In-Context-Learning-Based Text-to-SQL Errors 针对Text-to-SQL任务，提出MapleRepair框架，提升ICL错误修复的正确率和效率。 large language model
13 Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface Fun-tuning：利用微调接口评估专有LLM对优化型提示注入攻击的脆弱性 large language model
14 Mind the Inclusivity Gap: Multilingual Gender-Neutral Translation Evaluation with mGeNTE 提出mGeNTE资源，系统评估指令跟随语言模型在多语言性别中立翻译中的表现 instruction following

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

#题目一句话要点标签🔗⭐
15 A Simple Graph Contrastive Learning Framework for Short Text Classification 提出SimSTC，通过图对比学习解决短文本分类中的语义稀疏和噪声问题 contrastive learning large language model
16 Boosting Short Text Classification with Multi-Source Information Exploration and Dual-Level Contrastive Learning 提出MI-DELIGHT模型，通过多源信息探索和双层对比学习提升短文本分类性能。 contrastive learning large language model
17 FineMedLM-o1: Enhancing Medical Knowledge Reasoning Ability of LLM from Supervised Fine-Tuning to Test-Time Training FineMedLM-o1：通过监督微调与测试时训练提升LLM的医学知识推理能力 DPO direct preference optimization large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页