1 citations · 1 across the 8 of their papers we have counts for
5 papers · 1 filter
SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization
Weihan Meng, Hongzhu Guo, Yi Jing +5
Sparse autoencoders (SAEs) are proposed to extract numerous features from large language model (LLM) representations, yet explaining these features still relies primarily on extern…
TRAJDEBUG: Tracing Error Lifecycle to Identify Critical Failures in Long-Horizon Agent Trajectories
Yunjia Qi, Zehua Yin, Xintong Shi +10
LLM-based agentic systems have shown remarkable capabilities in complex domains, while suffering from cascading errors and difficulty in debugging. Critical error detection aims to…
Guiding LLM Post-training Data Engineering with Model Internals from Sparse Autoencoders
Yi Jing, Zao Dai, Jinwu Hu +4
Model internals encode rich information about how a large language model (LLM) processes its training data; however, post-training data engineering largely relies on external signa…
StoryAlign: Evaluating and Training Reward Models for Story Generation
Haotian Xia, Hao Peng, Yunjia Qi +4
Story generation aims to automatically produce coherent, structured, and engaging narratives. Although large language models (LLMs) have significantly advanced text generation, sto…
Understanding the Mechanism of Altruism in Large Language Models
Shuhuai Zhang, Shu Wang, Zijun Yao +4
Altruism is fundamental to human societies, fostering cooperation and social cohesion. While recent studies suggest that large language models (LLMs) can display human-like prosoci…