Look Before You Leap: Factual Decoding with Internal Attribution Signals

Paper recorded by Signals 4 on 2026-09-14 in cs.CL. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-14 on arXiv · recorded by Signals 4 on 2026-09-15

Category: cs.CL · 自然语言处理 · first seen 2026-09-15

Abstract

Hallucination remains a critical challenge in large language models (LLMs), where early factual errors compound through autoregressive generation in a snowballing effect that neither post-hoc correction nor weight-level intervention can effectively preempt. We propose DescaPE (DEcoding Signal Control Against Path Error-snowballing), a decoding framework that leverages internal model signals to sup

Read on arXiv →