cs.CL（2024-08-08）

📊 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) (19 🔗4) 支柱二：RL算法与架构 (RL & Architecture) (3)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (19 篇)

#题目一句话要点标签🔗⭐
1 Exploring Reasoning Biases in Large Language Models Through Syllogism: Insights from the NeuBAROCO Dataset NeuBAROCO数据集揭示大语言模型在三段论推理中存在与人类相似的推理偏差 large language model chain-of-thought
2 Hybrid Student-Teacher Large Language Model Refinement for Cancer Toxicity Symptom Extraction 提出混合师生大型语言模型优化方法，用于癌症毒性症状提取。 large language model
3 Learning Fine-Grained Grounded Citations for Attributed Large Language Models 提出FRONT框架，提升归因大语言模型细粒度引用质量，缓解幻觉问题 large language model
4 BA-LoRA: Bias-Alleviating Low-Rank Adaptation to Mitigate Catastrophic Inheritance in Large Language Models 提出BA-LoRA，缓解大语言模型微调中的灾难性继承问题。 large language model
5 Compromesso! Italian Many-Shot Jailbreaks Undermine the Safety of Large Language Models 意大利语多样本越狱攻击揭示大型语言模型安全漏洞 large language model
6 Recognizing Emotion Regulation Strategies from Human Behavior with Large Language Models 利用微调LLaMA2-7B识别羞耻情绪中的个体情绪调节策略，无需交互后访谈数据。 large language model
7 Automated Educational Question Generation at Different Bloom's Skill Levels using Large Language Models: Strategies and Evaluation 利用大型语言模型自动生成不同布鲁姆认知水平的教育问题 large language model
8 Open-domain Implicit Format Control for Large Language Model Generation 提出一种开放域隐式格式控制框架，利用少量示例提升大语言模型生成质量。 large language model ✅
9 Multi-Turn Context Jailbreak Attack on Large Language Models From First Principles 提出上下文融合攻击（CFA）方法，提升多轮对话场景下大语言模型的越狱攻击成功率。 large language model
10 Analysis of Argument Structure Constructions in the Large Language Model BERT 分析BERT对论证结构构造的处理机制 large language model
11 Conversational AI Powered by Large Language Models Amplifies False Memories in Witness Interviews 大型语言模型驱动的对话式AI在目击者访谈中显著增强虚假记忆 large language model
12 Enhancing Journalism with AI: A Study of Contextualized Image Captioning for News Articles using LLMs and LMMs 利用LLM和LMM增强新闻报道：针对新闻文章的上下文图像描述生成研究 large language model multimodal
13 Understanding the Performance and Estimating the Cost of LLM Fine-Tuning 分析MoE LLM微调性能并建立成本估算模型，助力高效LLM应用 large language model
14 Can LLMs Beat Humans in Debating? A Dynamic Multi-agent Framework for Competitive Debate 提出Agent4Debate，一个基于LLM的动态多智能体辩论框架，性能媲美人类 large language model
15 Synthetic SQL Column Descriptions and Their Impact on Text-to-SQL Performance 利用LLM生成SQL列描述提升Text-to-SQL性能，并构建了高质量的列描述数据集。 large language model
16 EMTeC: A Corpus of Eye Movements on Machine-Generated Texts EMTeC：一个用于研究机器生成文本上眼动行为的大规模语料库 large language model ✅
17 LLM-DetectAIve: a Tool for Fine-Grained Machine-Generated Text Detection LLM-DetectAIve：用于细粒度机器生成文本检测的工具 large language model ✅
18 Learning to Rewrite: Generalized LLM-Generated Text Detection 提出Learning2Rewrite框架，提升LLM生成文本检测在开放域的泛化能力。 large language model
19 ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities ToolSandbox：用于评估LLM工具使用能力的有状态、交互式基准测试 large language model ✅

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

#题目一句话要点标签🔗⭐
20 LaDiMo: Layer-wise Distillation Inspired MoEfier LaDiMo：一种受层间知识蒸馏启发的MoE模型构建方法，降低训练成本。 distillation large language model
21 Better Alignment with Instruction Back-and-Forth Translation 提出指令双向翻译方法，为LLM对齐构建高质量、基于世界知识的合成数据。 distillation large language model
22 Towards Resilient and Efficient LLMs: A Comparative Study of Efficiency, Performance, and Adversarial Robustness 研究高效LLM的效率、性能与鲁棒性权衡，探索简化架构的潜力 linear attention large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页