Pith. sign in

REVIEW 1 cited by

Learning to Correct for QA Reasoning with Black-box LLMs

Not yet reviewed by Pith; the record is open.

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 2406.18695 v2 pith:XVIU7W55 submitted 2024-06-26 cs.LG cs.AIcs.CL

classification cs.LGcs.AIcs.CL
keywords correctadaptationblack-boxreasoningreasoningsllmsmodelpairs
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

An open challenge in recent machine learning is about how to improve the reasoning capability of large language models (LLMs) in a black-box setting, i.e., without access to detailed information such as output token probabilities. Existing approaches either rely on accessibility (which is often unrealistic) or involve significantly increased train- and inference-time costs. This paper addresses those limitations or shortcomings by proposing a novel approach, namely CoBB (Correct for improving QA reasoning of Black-Box LLMs). It uses a trained adaptation model to perform a seq2seq mapping from the often-imperfect reasonings of the original black-box LLM to the correct or improved reasonings. Specifically, the adaptation model is initialized with a relatively small open-source LLM and adapted over a collection of sub-sampled training pairs. To select the representative pairs of correct and incorrect reasonings, we formulated the dataset construction as an optimization problem that minimizes the statistical divergence between the sampled subset and the entire collection, and solved it via a genetic algorithm. We then train the adaptation model over the sampled pairs by contrasting the likelihoods of correct and incorrect reasonings. Our experimental results demonstrate that CoBB significantly improves reasoning accuracy across various QA benchmarks, compared to the best-performing adaptation baselines.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

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

  1. Evolution of Thought: Diverse and High-Quality Reasoning via Multi-Objective Optimization

    cs.NE 2024-11 reject novelty 4.0 of 10

    EoT applies multi-objective evolutionary search with crossover, mutation, and clustering to MLLM reasoning and reports improved Pass@K accuracy on MathVista, Math-Vision, and GSM8K.

Pith tools