Pith. sign in

REVIEW 3 cited by

Memory-assisted prompt editing to improve GPT-3 after deployment

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2201.06009 v7 pith:VEC4LPYM submitted 2022-01-16 cs.CL

Aman Madaan , Niket Tandon , Peter Clark , Yiming Yang This is my paper · ORCID
classification cs.CL
keywords gpt-3usertaskscasesfeedbacklargememorymemprompt
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Large LMs such as GPT-3 are powerful, but can commit mistakes that are obvious to humans. For example, GPT-3 would mistakenly interpret "What word is similar to good?" to mean a homophone, while the user intended a synonym. Our goal is to effectively correct such errors via user interactions with the system but without retraining, which will be prohibitively costly. We pair GPT-3 with a growing memory of recorded cases where the model misunderstood the user's intents, along with user feedback for clarification. Such a memory allows our system to produce enhanced prompts for any new query based on the user feedback for error correction on similar cases in the past. On four tasks (two lexical tasks, two advanced ethical reasoning tasks), we show how a (simulated) user can interactively teach a deployed GPT-3, substantially increasing its accuracy over the queries with different kinds of misunderstandings by the GPT-3. Our approach is a step towards the low-cost utility enhancement for very large pre-trained LMs. Code, data, and instructions to implement MEMPROMPT for a new task at https://www.memprompt.com/.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Improving LLM-Based Fault Localization with External Memory and Project Context

    cs.SE 2025-06 conditional novelty 6.0 of 10

    MemFL gives an LLM static project summaries and dynamic debugging tips, and reports a 12.7% Top-1 accuracy gain over LLM fault localization baselines on Defects4J with lower time and cost.

  2. Break Through the Compression Bottleneck: From Theory to Practice

    cs.CL 2026-05 reject novelty 5.0 of 10

    The paper asserts a first proof that low-rank decomposition and quantization are non-orthogonal tools for LLM compression, recommends low-rank-first ordering, and adds a diagonal scaling fix (DAM) that reduces the com...

  3. Personalised Explanations in Long-term Human-Robot Interactions

    cs.RO 2025-07 conditional novelty 4.0 of 10

    A two-stage LLM pipeline that first generates an explanation and then personalises it using a stored user knowledge memory reduces explanation length only when the user has related prior knowledge, in synthetic hospit...

Pith tools