5 papers
Mapping Faithful Reasoning in Language Models
Jiazheng Li, Andreas Damianou, J Rosser +2
Chain-of-thought (CoT) traces promise transparency for reasoning language models, but prior work shows they are not always faithful reflections of internal computation. This raises…
NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database
Weizhi Fei, Hao Shi, Jing Xu +7
Efficiently editing knowledge stored in large language models (LLMs) enables model updates without large-scale training. One possible solution is Locate-and-Edit (L\&E), allowing s…
QuestA: Expanding Reasoning Capacity in LLMs via Question Augmentation
Jiazheng Li, Hongzhou Lin, Hong Lu +5
Reinforcement learning (RL) has emerged as a central paradigm for training large language models (LLMs) in reasoning tasks. Yet recent studies question RL's ability to incentivize…
Data Mixing Can Induce Phase Transitions in Knowledge Acquisition
Xinran Gu, Kaifeng Lyu, Jiazheng Li +1
Large Language Models (LLMs) are typically trained on data mixtures: most data come from web scrapes, while a small portion is curated from high-quality sources with dense domain-s…
Scalable Model Merging with Progressive Layer-wise Distillation
Jing Xu, Jiazheng Li, Jingzhao Zhang
Model merging offers an effective way to integrate the capabilities of multiple fine-tuned models. However, the performance degradation of the merged model remains a challenge, par…