← all papers · overview

Verifiable By Design: Aligning Language Models To Quote From Pre-training Data

Abstract

To trust the fluent generations of large language models (LLMs), humans must be able to verify their correctness against trusted, external sources. Recent efforts, such as providing citations via retrieved documents or post-hoc provenance, enhance verifiability but provide no guarantees on their correctness. To address these limitations, we tackle the verifiability goal with a different philosophy

Related papers

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