Pith. sign in

Instruction-tuned Language Models are Better Knowledge Learners

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
abstract

In order for large language model (LLM)-based assistants to effectively adapt to evolving information needs, it must be possible to update their factual knowledge through continued training on new data. The standard recipe for doing so involves continued pre-training on new documents followed by instruction-tuning on question-answer (QA) pairs. However, we find that LLMs trained with this recipe struggle to answer questions, even though the perplexity of documents is minimized. We found that QA pairs are generally straightforward, while documents are more complex, weaving many factual statements together in an intricate manner. Therefore, we hypothesize that it is beneficial to expose LLMs to QA pairs before continued pre-training on documents so that the process of encoding knowledge from complex documents takes into account how this knowledge is accessed through questions. Based on this, we propose pre-instruction-tuning (PIT), a method that instruction-tunes on questions prior to training on documents. This contrasts with standard instruction-tuning, which learns how to extract knowledge after training on documents. Extensive experiments and ablation studies demonstrate that pre-instruction-tuning significantly enhances the ability of LLMs to absorb knowledge from new documents, outperforming standard instruction-tuning by 17.8%.

citation-role summary

method 1

citation-polarity summary

fields

cs.CL 1

years

2025 1

verdicts

REJECT 1

roles

method 1

polarities

use method 1

representative citing papers

citing papers explorer

Showing 1 of 1 citing paper.

  • ScienceMeter: Tracking Scientific Knowledge Updates in Language Models cs.CL · 2025-05-30 · reject · none · ref 24 · internal anchor

    ScienceMeter evaluates language model knowledge updates across three axes, preservation of old scientific claims, acquisition of new claims, and projection to future findings, and finds all current methods fall short.