cs.CL（2024-09-24）

📊 共 24 篇论文 | 🔗 8 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (20 🔗7) 支柱二：RL算法与架构 (RL & Architecture) (2 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (1) 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 FMDLlama: Financial Misinformation Detection based on Large Language Models FMDLlama：基于Llama3.1微调的金融虚假信息检测大语言模型 large language model instruction following ✅
2 HelloBench: Evaluating Long Text Generation Capabilities of Large Language Models HelloBench：评估大型语言模型长文本生成能力的综合基准 large language model ✅
3 Enhancing Text-to-SQL Capabilities of Large Language Models via Domain Database Knowledge Injection 提出领域数据库知识注入方法，提升大语言模型在Text-to-SQL任务中的能力。 large language model
4 Exploring the traditional NMT model and Large Language Model for chat translation 提出基于MBR自训练的模型以提升聊天翻译性能 large language model
5 CHBench: A Chinese Dataset for Evaluating Health in Large Language Models 提出CHBench：首个面向中文大语言模型健康安全评估的综合基准 large language model ✅
6 XTRUST: On the Multilingual Trustworthiness of Large Language Models XTRUST：首个多语言大语言模型可信度评测基准 large language model ✅
7 Bridging Speech and Text: Enhancing ASR with Pinyin-to-Character Pre-training in LLMs 提出基于拼音-汉字预训练的大语言模型，提升语音识别性能 large language model multimodal
8 Strategies for Improving NL-to-FOL Translation with LLMs: Data Generation, Incremental Fine-Tuning, and Verification 提出数据生成、增量微调和验证策略，提升LLM的NL-to-FOL翻译性能 large language model
9 A Comprehensive Survey of Bias in LLMs: Current Landscape and Future Directions 全面综述LLM中的偏见：现状与未来方向 large language model
10 Controlling Risk of Retrieval-augmented Generation: A Counterfactual Prompting Framework 提出基于反事实提示的RAG风险控制框架，提升模型置信度评估能力 large language model ✅
11 AI Can Be Cognitively Biased: An Exploratory Study on Threshold Priming in LLM-Based Batch Relevance Assessment 研究表明：LLM在批量相关性评估中存在阈值启动效应认知偏差 large language model
12 Finetuning LLMs for Comparative Assessment Tasks 微调LLM用于比较评估任务，提升效率与性能 large language model
13 SLIMER-IT: Zero-Shot NER on Italian Language 提出SLIMER-IT，一种面向意大利语的零样本命名实体识别方法。 large language model
14 HLB: Benchmarking LLMs' Humanlikeness in Language Use HLB：构建LLM语言使用人性的综合评测基准 large language model ✅
15 NER-Luxury: Named entity recognition for the fashion and luxury domain 提出NER-Luxury模型以解决时尚奢侈品领域命名实体识别问题 large language model
16 Small Language Models: Survey, Measurements, and Insights 全面评测与分析小型语言模型，洞察设备端智能的未来 large language model
17 Making Text Embedders Few-Shot Learners 提出bge-en-icl模型，利用LLM的ICL能力提升文本嵌入质量，达到SOTA性能。 large language model ✅
18 A Survey of Stance Detection on Social Media: New Directions and Perspectives 社交媒体立场检测综述：探讨新方向与未来视角 large language model
19 FLEX: Expert-level False-Less EXecution Metric for Reliable Text-to-SQL Benchmark FLEX：一种专家级无误判的Text-to-SQL评估指标，提升基准测试可靠性 large language model
20 Qualitative Insights Tool (QualIT): LLM Enhanced Topic Modeling QualIT：利用LLM增强主题建模，提升主题连贯性和多样性 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🔗⭐
21 Do the Right Thing, Just Debias! Multi-Category Bias Mitigation Using LLMs 利用LLM进行多类别偏见缓解：提出ANUBIS数据集并探索多种去偏方法 reinforcement learning PPO DPO
22 Privacy Evaluation Benchmarks for NLP Models 构建NLP模型隐私评估基准，提升隐私攻击与防御的系统性分析能力 distillation large language model ✅

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗⭐
23 A Zero-Shot Open-Vocabulary Pipeline for Dialogue Understanding 提出零样本开放词汇对话理解流水线，提升任务型对话系统性能。 open-vocabulary open vocabulary large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
24 Unveiling Language Competence Neurons: A Psycholinguistic Approach to Model Interpretability 利用心理语言学范式揭示语言模型中蕴含语言能力的神经元 manipulation large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页