6 papers
Read As Human: Compressing Context via Parallelizable Close Reading and Skimming
Jiwei Tang, Shilei Liu, Zhicheng Zhang +9
Large Language Models (LLMs) demonstrate exceptional capability across diverse tasks. However, their deployment in long-context scenarios is hindered by two challenges: computation…
RAISE: Reinforced Adaptive Instruction Selection For Large Language Models
Qingsong Lv, Yangning Li, Zihua Lan +8
In the instruction fine-tuning of large language models (LLMs), it is widely recognized that a few high-quality instructions are superior to a large number of low-quality instructi…
Diagnosing Failures in Large Language Models' Answers: Integrating Error Attribution into Evaluation Framework
Zishan Xu, Shuyi Xie, Qingsong Lv +4
With the widespread application of Large Language Models (LLMs) in various tasks, the mainstream LLM platforms generate massive user-model interactions daily. In order to efficient…
RLVER: Reinforcement Learning with Verifiable Emotion Rewards for Empathetic Agents
Peisong Wang, Ruotian Ma, Bang Zhang +13
Large language models (LLMs) excel at logical and algorithmic reasoning, yet their emotional intelligence (EQ) still lags far behind their cognitive prowess. While reinforcement le…
UltraWiki: Ultra-fine-grained Entity Set Expansion with Negative Seed Entities
Yangning Li, Qingsong Lv, Tianyu Yu +5
Entity Set Expansion (ESE) aims to identify new entities belonging to the same semantic class as the given set of seed entities. Traditional methods solely relied on positive seed…
MDIT: A Model-free Data Interpolation Method for Diverse Instruction Tuning
Yangning Li, Zihua Lan, Lv Qingsong +2
As Large Language Models (LLMs) are increasingly applied across various tasks, instruction tuning has emerged as a critical method for enhancing model performance. However, current…