← all papers · overview

Varying Shades Of Wrong: Aligning Llms With Wrong Answers Only

Abstract

In the absence of abundant reliable annotations for challenging tasks and contexts, how can we expand the frontier of LLM capabilities with potentially wrong answers? We focus on two research questions: (1) Can LLMs generate reliable preferences among wrong options? And if so, (2) Would alignment with such wrong-over-wrong preferences be helpful? We employ methods based on self-consistency, token

Related papers

Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).