| 1 |
Layered Chain-of-Thought Prompting for Multi-Agent LLM Systems: A Comprehensive Approach to Explainable Large Language Models |
提出分层思维链提示（Layered-CoT），提升多智能体LLM系统解释性和可靠性 |
large language model chain-of-thought |
|
|
| 2 |
InnerThoughts: Disentangling Representations and Predictions in Large Language Models |
InnerThoughts：解耦大语言模型中的表征与预测能力，提升问答性能 |
large language model |
|
|
| 3 |
Semantic Consistency Regularization with Large Language Models for Semi-supervised Sentiment Analysis |
提出基于大语言模型语义一致性正则化的半监督情感分析方法 |
large language model |
|
|
| 4 |
GLLM: Self-Corrective G-Code Generation using Large Language Models with User Feedback |
GLLM：利用大语言模型和用户反馈实现自校正G代码生成 |
large language model |
|
|
| 5 |
Exploring Vision Language Models for Multimodal and Multilingual Stance Detection |
评估视觉语言模型在多模态多语言立场检测中的性能与局限性 |
multimodal |
|
|
| 6 |
Context-Aware Semantic Recomposition Mechanism for Large Language Models |
提出上下文感知语义重组机制CASRM，提升大语言模型在文本生成中的连贯性和适应性。 |
large language model |
|
|
| 7 |
Structured Context Recomposition for Large Language Models Using Probabilistic Layer Realignment |
提出结构化上下文重组方法，通过概率层重对齐增强大语言模型长文本一致性。 |
large language model |
|
|
| 8 |
Query-Aware Learnable Graph Pooling Tokens as Prompt for Large Language Models |
提出LGPT：一种查询感知的可学习图池化Token方法，用于增强大语言模型处理图数据的能力 |
large language model |
|
|
| 9 |
Prompt-oriented Output of Culture-Specific Items in Translated African Poetry by Large Language Model: An Initial Multi-layered Tabular Review |
通过提示工程评估大型语言模型在非洲诗歌翻译中文化元素的生成能力 |
large language model |
|
|
| 10 |
CSEval: Towards Automated, Multi-Dimensional, and Reference-Free Counterspeech Evaluation using Auto-Calibrated LLMs |
提出CSEval以解决自动化反言论评估标准缺失问题 |
large language model chain-of-thought |
|
|
| 11 |
MultiChallenge: A Realistic Multi-Turn Conversation Evaluation Benchmark Challenging to Frontier LLMs |
MultiChallenge：一个评估LLM多轮对话能力的真实基准 |
large language model instruction following |
|
|
| 12 |
In-Context Meta LoRA Generation |
提出ICM-LoRA，通过上下文元学习生成任务相关的LoRA参数，实现高效的大语言模型定制。 |
large language model |
|
|
| 13 |
Learning Beyond the Surface: How Far Can Continual Pre-Training with LoRA Enhance LLMs' Domain-Specific Insight Learning? |
LoRA持续预训练提升LLM领域知识洞察力：医学与金融案例研究 |
large language model |
|
|
| 14 |
Reasoning Over the Glyphs: Evaluation of LLM's Decipherment of Rare Scripts |
提出多模态数据集和方法，评估LLM在解读未编码稀有文字方面的能力 |
multimodal |
|
|
| 15 |
2SSP: A Two-Stage Framework for Structured Pruning of LLMs |
提出2SSP框架，结合宽度和深度剪枝，高效压缩大型语言模型。 |
large language model |
✅ |
|
| 16 |
Actions Speak Louder than Words: Agent Decisions Reveal Implicit Biases in Language Models |
通过Agent决策揭示语言模型中基于社会人口属性的隐性偏见 |
large language model |
|
|
| 17 |
Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate |
提出批判微调（CFT），通过学习批判而非模仿提升语言模型推理能力 |
instruction following |
|
|
| 18 |
Uncertainty Quantification and Decomposition for LLM-based Recommendation |
提出不确定性量化与分解框架，评估并提升LLM推荐的可靠性 |
large language model |
✅ |
|