cs.CL（2026-02-24）

📊 共 15 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (8) 支柱二：RL算法与架构 (RL & Architecture) (7 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (8 篇)

#题目一句话要点标签🔗⭐
1 Evaluating Proactive Risk Awareness of Large Language Models 提出Butterfly数据集与评估框架，衡量LLM在生态环境领域的风险预警能力 large language model multimodal
2 An Expert Schema for Evaluating Large Language Model Errors in Scholarly Question-Answering Systems 提出专家评估模式，用于评估大型语言模型在学术问答系统中的错误 large language model
3 Linear Reasoning vs. Proof by Cases: Obstacles for Large Language Models in FOL Problem Solving 提出PC-FOL数据集，揭示大语言模型在基于案例推理的FOL问题求解中的局限性 large language model
4 CARE: An Explainable Computational Framework for Assessing Client-Perceived Therapeutic Alliance Using Large Language Models 提出CARE框架，利用大语言模型评估客户端感知的治疗联盟，并提供可解释性。 large language model
5 From Performance to Purpose: A Sociotechnical Taxonomy for Evaluating Large Language Model Utility 提出LUX框架，用于多维度评估大语言模型在实际应用中的效用 large language model
6 Blackbird Language Matrices: A Framework to Investigate the Linguistic Competence of Language Models 提出黑鸟语言矩阵（BLM）任务，用于评估语言模型的语言能力。 large language model
7 ID-LoRA: Efficient Low-Rank Adaptation Inspired by Matrix Interpolative Decomposition ID-LoRA：一种受矩阵插值分解启发的参数高效低秩自适应方法 large language model
8 SpecMind: Cognitively Inspired, Interactive Multi-Turn Framework for Postcondition Inference SpecMind：认知驱动的交互式多轮后置条件推断框架 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (7 篇)

#题目一句话要点标签🔗⭐
9 Overton Pluralistic Reinforcement Learning for Large Language Models 提出OP-GRPO，使大语言模型在无显式提示下生成多元化回复，提升观点覆盖率。 reinforcement learning large language model
10 The Art of Efficient Reasoning: Data, Reward, and Optimization 提出高效推理训练方法，通过数据、奖励和优化策略提升LLM推理效率。 reinforcement learning reward shaping large language model
11 Prompt-Level Distillation: A Non-Parametric Alternative to Model Fine-Tuning for Efficient Reasoning 提出Prompt-Level Distillation，无需微调即可高效推理，提升小模型性能。 distillation chain-of-thought
12 Don't Ignore the Tail: Decoupling top-K Probabilities for Efficient Language Model Distillation 提出解耦Top-K概率的蒸馏方法，提升语言模型蒸馏效率。 distillation
13 CAMEL: Confidence-Gated Reflection for Reward Modeling 提出CAMEL：一种置信度门控的自反思奖励建模框架，提升奖励模型的效率和准确性。 reinforcement learning large language model
14 On Data Engineering for Scaling LLM Terminal Capabilities 提出Terminal-Task-Gen和Terminal-Corpus，显著提升LLM在终端任务中的能力。 curriculum learning large language model ✅
15 Generative Pseudo-Labeling for Pre-Ranking with LLMs 提出GPL框架，利用LLM生成伪标签解决预排序中的训练-服务偏差问题 distillation large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页