Learning to Edit: Aligning LLMs with Knowledge Editing

Anonymous

Abstract: Knowledge editing techniques, aiming to efficiently modify a minor proportion of knowledge in large language models (LLMs) without negatively impacting performance across other inputs, have garnered widespread attention. However, existing methods predominantly rely on memorizing the updated knowledge, impeding LLMs from effectively combining the new knowledge with their inherent knowledge when answering questions. To this end, we propose a Learning to Edit (LTE) framework, focusing on teaching LLMs to apply updated knowledge into input questions, inspired by the philosophy of "Teach a man to fish." LTE features a two-phase process: (i) the Alignment Phase, which fine-tunes LLMs on a meticulously curated parallel dataset to make reliable, in-scope edits while preserving out-of-scope information and linguistic proficiency; and (ii) the Inference Phase, which employs a retrieval-based mechanism for real-time and mass knowledge editing. By comparing our approach with seven advanced baselines across four popular knowledge editing benchmarks and two LLM architectures, we demonstrate LTE's superiority in knowledge editing performance, robustness in both batch and sequential editing, minimal interference on general tasks, and rapid editing speeds. The data and code will be publicly available.

Paper Type: long

Research Area: NLP Applications

Contribution Types: NLP engineering experiment, Publicly available software and/or pre-trained models, Data resources

Languages Studied: English

Preprint Status: We plan to release a non-anonymous preprint in the next two months (i.e., during the reviewing process).

A1: yes

A1 Elaboration For Yes Or No: In the Section of Limitations.

A2: yes

A2 Elaboration For Yes Or No: In the Section of Ethics Statement.

A3: yes

A3 Elaboration For Yes Or No: In the Section of Abstract and Introduction.

B: yes

B1: yes

B1 Elaboration For Yes Or No: In Section 4.1 and 4.4.

B2: n/a

B3: n/a

B4: n/a

B5: n/a

B6: yes

B6 Elaboration For Yes Or No: In Section 4.1.

C: yes

C1: yes

C1 Elaboration For Yes Or No: In Section 4.1 and Appendix D.

C2: yes

C2 Elaboration For Yes Or No: In Section 4.1 and Appendix D.

C3: yes

C3 Elaboration For Yes Or No: In Section 4.

C4: yes

C4 Elaboration For Yes Or No: In Section 4.1 and 4.4.

D: no

D1: n/a

D2: n/a

D3: n/a

D4: n/a

D5: n/a

E: no

E1: n/a