| 1 |
Multi-ToM: Evaluating Multilingual Theory of Mind Capabilities in Large Language Models |
Multi-ToM：评估大型语言模型在多语言环境下的心理理论能力 |
large language model |
|
|
| 2 |
Evaluating Large Language Models for Causal Modeling |
利用大型语言模型进行因果建模任务评估与分析 |
large language model |
|
|
| 3 |
A Method for Building Large Language Models with Predefined KV Cache Capacity |
提出有界缓存Transformer（BCT），解决大语言模型KV缓存容量限制问题 |
large language model |
|
|
| 4 |
RAMIE: Retrieval-Augmented Multi-task Information Extraction with Large Language Models on Dietary Supplements |
提出RAMIE框架，利用检索增强的多任务LLM提升膳食补充剂信息抽取性能 |
large language model |
|
|
| 5 |
Investigating Factuality in Long-Form Text Generation: The Roles of Self-Known and Self-Unknown |
研究长文本生成的事实性问题，分析模型自知与自不知能力的影响。 |
large language model |
|
|
| 6 |
Generative Prompt Internalization |
提出生成式Prompt内化方法GenPI，解决大模型应用中Prompt过长导致的计算开销问题。 |
large language model |
|
|
| 7 |
Do LLMs Really Think Step-by-step In Implicit Reasoning? |
研究表明：提示式隐式思维链难以实现真正的逐步推理 |
chain-of-thought |
|
|
| 8 |
LoRA-Mini : Adaptation Matrices Decomposition and Selective Training |
LoRA-Mini：通过分解和选择性训练自适应矩阵，实现更高效的参数微调 |
large language model |
|
|
| 9 |
LLaMA-MoE v2: Exploring Sparsity of LLaMA from Perspective of Mixture-of-Experts with Post-Training |
通过后训练探索LLaMA模型的稀疏性，构建高效MoE模型 |
large language model |
✅ |
|