cs.CL（2026-02-21）
📊 共 6 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) (6 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | ArabicNumBench: Evaluating Arabic Number Reading in Large Language Models | ArabicNumBench：评估大型语言模型在阿拉伯语数字阅读任务中的性能 | large language model instruction following chain-of-thought | ||
| 2 | Think$^{2}$: Grounded Metacognitive Reasoning in Large Language Models | Think$^{2}$：提出基于认知理论的元认知框架，提升大语言模型推理和自我纠错能力 | large language model chain-of-thought | ||
| 3 | BURMESE-SAN: Burmese NLP Benchmark for Evaluating Large Language Models | 提出BURMESE-SAN，用于系统评估大型语言模型在缅甸语上的理解、推理和生成能力。 | large language model | ||
| 4 | ReHear: Iterative Pseudo-Label Refinement for Semi-Supervised Speech Recognition via Audio Large Language Models | 提出ReHear框架，利用音频大语言模型迭代优化伪标签，提升半监督语音识别性能。 | large language model | ||
| 5 | DeepInnovator: Triggering the Innovative Capabilities of LLMs | 提出DeepInnovator以激发大语言模型的创新能力 | large language model | ✅ | |
| 6 | Contradiction to Consensus: Dual Perspective, Multi Source Retrieval Based Claim Verification with Source Level Disagreement using LLM | 提出基于双重视角和多源检索的声明验证系统，利用LLM分析来源层面的不一致性。 | large language model |