1 citations · 1 across the 3 of their papers we have counts for
14 papers
How LLM Task-Adaptation Reshapes Alignment: A Multi-dimensional Study of Behavioral and Representational Drift
James Elcock, William F. Shen, Xinchi Qiu +1
Post-training is a key mechanism for adapting large language models to downstream tasks. While prior work suggests that task adaptation can alter a model's pre-existing alignment,…
LoRDO: Distributed Low-Rank Optimization with Infrequent Communication
Andrej JovanoviÄ, Alex Iacob, Mher Safaryan +6
Distributed training of foundation models via is limited by interconnect bandwidth. While infrequent communication strategies reduce synchronization frequency, they…
Photon: Federated LLM Pre-Training
Lorenzo Sani, Alex Iacob, Zeyu Cao +8
Scaling large language models (LLMs) demands extensive data and computing resources, which are traditionally constrained to data centers by the high-bandwidth requirements of distr…
SEAT: Sparse Entity-Aware Tuning for Knowledge Adaptation while Preserving Epistemic Abstention
William F. Shen, Xinchi Qiu, Nicola Cancedda +1
Adapting LLMs with new knowledge is increasingly important, but standard fine-tuning often erodes aligned epistemic abstention: the ability to acknowledge when the model does not k…
Rethinking Rubric Generation for Improving LLM Judge and Reward Modeling for Open-ended Tasks
William F. Shen, Xinchi Qiu, Chenxi Whitehouse +6
Recently, rubrics have been used to guide LLM judges in capturing subjective, nuanced, multi-dimensional human preferences, and have been extended from evaluation to reward signals…
Hallucination reduction with CASAL: Contrastive Activation Steering For Amortized Learning
Wannan, Yang, Xinchi Qiu +6
Large Language Models (LLMs) exhibit impressive capabilities but often hallucinate, confidently providing incorrect answers instead of admitting ignorance. Prior work has shown tha…