cs.CL（2024-08-22）

📊 共 22 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) (16 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (5) 支柱一：机器人控制 (Robot Control) (1 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (16 篇)

#题目一句话要点标签🔗⭐
1 MaVEn: An Effective Multi-granularity Hybrid Visual Encoding Framework for Multimodal Large Language Model MaVEn：一种用于多模态大语言模型的多粒度混合视觉编码框架，提升多图推理能力 large language model multimodal
2 NUS-Emo at SemEval-2024 Task 3: Instruction-Tuning LLM for Multimodal Emotion-Cause Analysis in Conversations NUS-Emo提出指令调优LLM用于对话多模态情感原因分析，SemEval-2024 Task 3排名第二。 large language model multimodal
3 Implicit Sentiment Analysis Based on Chain of Thought Prompting 提出基于思维链提示的隐式情感分析框架SAoT，提升情感极性推断性能。 large language model chain-of-thought
4 Towards Evaluating and Building Versatile Large Language Models for Medicine 提出MedS-Bench医学评测基准与MedS-Ins指令调优数据集，提升LLM在医疗领域的应用能力 large language model ✅
5 GenderCARE: A Comprehensive Framework for Assessing and Reducing Gender Bias in Large Language Models GenderCARE框架：全面评估并降低大型语言模型中的性别偏见 large language model ✅
6 Enhancing Multi-hop Reasoning through Knowledge Erasure in Large Language Model Editing 提出KELE：通过知识擦除增强大语言模型在多跳推理中的知识编辑能力 large language model
7 Improving Factuality in Large Language Models via Decoding-Time Hallucinatory and Truthful Comparators 提出Comparator-driven Decoding-Time框架，提升大语言模型生成内容的真实性。 large language model
8 Toward the Evaluation of Large Language Models Considering Score Variance across Instruction Templates 提出考虑指令模板方差的LLM评估方法，解决NLU性能评估不公平问题 large language model
9 Large Language Models as Foundations for Next-Gen Dense Retrieval: A Comprehensive Empirical Assessment 大规模语言模型赋能下一代稠密检索：一项全面的实证评估 large language model
10 Reasoning Factual Knowledge in Structured Data with Large Language Models 提出StructFact基准，评估大语言模型在结构化数据中推理事实知识的能力 large language model ✅
11 SLM Meets LLM: Balancing Latency, Interpretability and Consistency in Hallucination Detection 提出SLM与LLM结合框架，平衡幻觉检测的延迟、可解释性和一致性 large language model
12 Macro-Queries: An Exploration into Guided Chart Generation from High Level Prompts 提出基于LLM的引导式图表生成流程，提升非专业用户数据可视化能力 large language model
13 Urban Mobility Assessment Using LLMs 利用大型语言模型合成出行调查数据，评估城市交通模式。 large language model
14 A Comparative Analysis of Faithfulness Metrics and Humans in Citation Evaluation 提出比较评估框架以解决引用支持评估的挑战 large language model
15 EvalYaks: Instruction Tuning Datasets and LoRA Fine-tuned Models for Automated Scoring of CEFR B2 Speaking Assessment Transcripts EvalYaks：指令微调Mistral 7B，实现CEFR B2口语评估的自动化评分 large language model
16 Understanding Literary Texts by LLMs: A Case Study of Ancient Chinese Poetry 利用大语言模型理解文学文本：以中国古诗词为例 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#题目一句话要点标签🔗⭐
17 FIRST: Teach A Reliable Large Language Model Through Efficient Trustworthy Distillation 提出FIRST：通过高效可信的蒸馏方法训练可靠的大型语言模型 distillation large language model
18 RuleAlign: Making Large Language Models Better Physicians with Diagnostic Rule Alignment RuleAlign：通过诊断规则对齐提升大型语言模型在医疗诊断中的表现 preference learning large language model
19 Jamba-1.5: Hybrid Transformer-Mamba Models at Scale Jamba-1.5：基于混合Transformer-Mamba架构的大规模语言模型，实现高吞吐和低内存占用。 Mamba large language model instruction following
20 Interactive DualChecker for Mitigating Hallucinations in Distilling Large Language Models 提出 DualChecker 框架，缓解大语言模型蒸馏中的幻觉问题并提升模型性能。 distillation large language model
21 Preference-Guided Reflective Sampling for Aligning Language Models 提出偏好引导反射采样(PRS)，提升语言模型与人类偏好对齐效果 offline RL large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
22 Controllable Text Generation for Large Language Models: A Survey 综述可控文本生成：针对大语言模型，实现内容与属性的精准控制。 manipulation reinforcement learning large language model ✅

⬅️ 返回 cs.CL 首页 · 🏠 返回主页