most citedState Rank Dynamics in Linear Attention LLMs

1 citations · 1 across the 3 of their papers we have counts for

collaborators
Showing cs.CLShow all

2 papers · 1 filter

cs.CL2026

A Controlled Study of Decoding-Time Truthfulness Methods on Instruction-Tuned LLMs

Ao Sun

Decoding-time truthfulness methods -- layer-contrast decoding, inference-time intervention, and learned logit adapters -- have demonstrated 10-30 point gains on TruthfulQA when app…

cs.CL2025

CHAIR -- Classifier of Hallucination as Improver

Ao Sun

In this work, we introduce CHAIR (Classifier of Hallucination As ImproveR), a supervised framework for detecting hallucinations by analyzing internal logits from each layer of ever…