cs.CL（2025-01-06）

📊 共 15 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) (11 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (4)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (11 篇)

#题目一句话要点标签🔗⭐
1 BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning BoostStep：通过改进单步推理提升大语言模型的数学能力 large language model chain-of-thought
2 LangFair: A Python Package for Assessing Bias and Fairness in Large Language Model Use Cases LangFair：用于评估大型语言模型偏见和公平性的Python软件包 large language model
3 Semantic Captioning: Benchmark Dataset and Graph-Aware Few-Shot In-Context Learning for SQL2Text 提出基于图感知的少样本上下文学习方法，用于SQL查询到自然语言描述的生成。 large language model ✅
4 PRMBench: A Fine-grained and Challenging Benchmark for Process-Level Reward Models PRMBench：一个用于过程级奖励模型细粒度和挑战性的评测基准 large language model
5 Graph-based Retrieval Augmented Generation for Dynamic Few-shot Text Classification 提出GORAG：一种基于图检索增强生成框架，用于动态少样本文本分类 large language model
6 Detecting AI-Generated Text in Educational Content: Leveraging Machine Learning and Explainable AI for Academic Integrity 利用机器学习和可解释AI检测教育内容中AI生成文本，提升学术诚信 large language model
7 Leveraging Explainable AI for LLM Text Attribution: Differentiating Human-Written and Multiple LLMs-Generated Text 利用可解释AI进行LLM文本溯源，区分人类撰写和多种LLM生成文本 large language model
8 CLIX: Cross-Lingual Explanations of Idiomatic Expressions 提出CLIX任务，利用跨语言解释成语，辅助语言学习者词汇扩展。 large language model
9 VicSim: Enhancing Victim Simulation with Emotional and Linguistic Fidelity VicSim：通过情感和语言保真度增强受害者模拟，用于情景训练。 large language model
10 Sentiment-guided Commonsense-aware Response Generation for Mental Health Counseling 提出EmpRes，一种情感引导的常识感知回复生成方法，用于心理健康咨询。 foundation model
11 ADePT: Adaptive Decomposed Prompt Tuning for Parameter-Efficient Fine-tuning 提出ADePT，通过自适应分解Prompt调整，提升参数高效微调性能。 large language model ✅

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

#题目一句话要点标签🔗⭐
12 IIMedGPT: Promoting Large Language Model Capabilities of Medical Tasks by Efficient Human Preference Alignment IIMedGPT：通过高效人类偏好对齐提升大型语言模型在医疗任务中的能力 DPO direct preference optimization large language model
13 InfiFusion: A Unified Framework for Enhanced Cross-Model Reasoning via LLM Fusion InfiFusion：通过LLM融合增强跨模型推理的统一框架 distillation large language model instruction following
14 Segmenting Text and Learning Their Rewards for Improved RLHF in Language Model 提出基于文本片段奖励的强化学习方法，提升语言模型的人工反馈对齐效果 reinforcement learning RLHF
15 MBTSAD: Mitigating Backdoors in Language Models Based on Token Splitting and Attention Distillation 提出MBTSAD，一种无需预训练权重即可缓解语言模型后门攻击的方法 distillation

⬅️ 返回 cs.CL 首页 · 🏠 返回主页