cs.CL（2025-04-20）

📊 共 11 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) (9 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (9 篇)

#	题目	一句话要点	标签	🔗	⭐
1	FarsEval-PKBETS: A new diverse benchmark for evaluating Persian large language models	FarsEval-PKBETS：一个用于评估波斯语大型语言模型的新型多样化基准	large language model
2	PROMPTEVALS: A Dataset of Assertions and Guardrails for Custom Production Large Language Model Pipelines	PROMPTEVALS：用于定制化生产大语言模型流水线的断言与护栏数据集	large language model
3	Trans-Zero: Self-Play Incentivizes Large Language Models for Multilingual Translation Without Parallel Data	提出TRANS-ZERO，利用自博弈和大型语言模型实现无需平行数据的多语言翻译	large language model
4	A Hierarchical Framework for Measuring Scientific Paper Innovation via Large Language Models	提出基于大语言模型的层级框架HSPIM，用于评估科学论文的创新性。	large language model	✅
5	Functional Abstraction of Knowledge Recall in Large Language Models	通过函数抽象理解LLM知识回忆机制，并改进上下文知识编辑	large language model
6	a1: Steep Test-time Scaling Law via Environment Augmented Generation	提出环境增强生成（EAG）框架，提升LLM在复杂推理任务中的可靠性与准确性。	large language model chain-of-thought
7	Causality for Natural Language Processing	深入探索大型语言模型中的因果推理能力及其在自然语言处理中的应用	large language model
8	BookWorld: From Novels to Interactive Agent Societies for Creative Story Generation	BookWorld：构建小说世界交互式智能体社会，用于创造性故事生成。	large language model	✅
9	Don't Retrieve, Generate: Prompting LLMs for Synthetic Training Data in Dense Retrieval	提出利用LLM生成合成负样本训练稠密检索模型，但效果不如传统方法。	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	🔗	⭐
10	Knowledge Distillation and Dataset Distillation of Large Language Models: Emerging Trends, Challenges, and Future Directions	综述：知识蒸馏与数据集蒸馏协同压缩大语言模型，应对算力与数据挑战。	distillation large language model
11	sEEG-based Encoding for Sentence Retrieval: A Contrastive Learning Approach to Brain-Language Alignment	SSENSE：基于sEEG的对比学习框架，实现脑活动与自然语言的对齐和句子检索	contrastive learning foundation model multimodal

⬅️ 返回 cs.CL 首页 · 🏠 返回主页