# Learning to Correct for QA Reasoning with Black-box LLMs

arXiv: https://arxiv.org/abs/2406.18695 · HTML: https://mlsanity.com/paper/2406.18695/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning.
- Builds on 17 of its 56 references that are in the map.
- First posted on arXiv 26 Jun 2024.

## Placed in

- LLM reasoning / [Test-time compute and efficient thinking](https://mlsanity.com/lr/test-time-compute-and-efficient-thinking/)

## Builds on (most cited first, 17 of 17)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [Gemma: Open Models Based on Gemini Research and Technology](https://mlsanity.com/paper/2403.08295/) (2024)
- [Gemini: A Family of Highly Capable Multimodal Models](https://mlsanity.com/paper/2312.11805/) (2023)
- [ORPO: Monolithic Preference Optimization without Reference Model](https://mlsanity.com/paper/2403.07691/) (2024)
- [LaMP: When Large Language Models Meet Personalization](https://mlsanity.com/paper/2304.11406/) (2023)
- [Towards Expert-Level Medical Question Answering with Large Language Models](https://mlsanity.com/paper/2305.09617/) (2023)
- [Large Language Model Unlearning](https://mlsanity.com/paper/2310.10683/) (2023)
- [V-STaR: Training Verifiers for Self-Taught Reasoners](https://mlsanity.com/paper/2402.06457/) (2024)
- [Aligner: Efficient Alignment by Learning to Correct](https://mlsanity.com/paper/2402.02416/) (2024)
- [Democratizing Large Language Models via Personalized Parameter-Efficient Fine-tuning](https://mlsanity.com/paper/2402.04401/) (2024)
- [Tuning Language Models by Proxy](https://mlsanity.com/paper/2401.08565/) (2024)
- [Bias Mitigation in Fine-tuning Pre-trained Models for Enhanced Fairness and Efficiency](https://mlsanity.com/paper/2403.00625/) (2024)

## Built on by (most cited first, 6 of 6)

- [What's Wrong? Refining Meeting Summaries with LLM Feedback](https://mlsanity.com/paper/2407.11919/) (2024)
- [When Agents Fail: A Comprehensive Study of Bugs in LLM Agents with Automated Labeling](https://mlsanity.com/paper/2601.15232/) (2026)
- [Question Answering with LLMs and Learning from Answer Sets](https://mlsanity.com/paper/2509.16590/) (2025)
- [DICE: Structured Reasoning in LLMs through SLM-Guided Chain-of-Thought Correction](https://mlsanity.com/paper/2510.09211/) (2025)
- [Evolution of Thought: Diverse and High-Quality Reasoning via Multi-Objective Optimization](https://mlsanity.com/paper/2412.07779/) (2024)
- [Probing Cultural Awareness in LLMs: A Case Study of Cross-Culture Aesthetic Stylistics](https://mlsanity.com/paper/2605.27296/) (2026)

## Abstract (arXiv)

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.