mlsanityData to 7 Oct 2026

Using Interactive Feedback to Improve the Accuracy and Explainability of Question Answering Systems Post-Deployment

arXiv 2204.03025 ↗First posted 6 Apr 2022cs.CLcited by 25

Not on the map. Why?

Abstract (arXiv)

Most research on question answering focuses on the pre-deployment stage; i.e., building an accurate model for deployment. In this paper, we ask the question: Can we improve QA systems further post-deployment based on user interactions? We focus on two kinds of improvements: 1) improving the QA system's performance itself, and 2) providing the model with the ability to explain the correctness or incorrectness of an answer. We collect a retrieval-based QA dataset, FeedbackQA, which contains interactive feedback from users. We collect this dataset by deploying a base QA system to crowdworkers who then engage with the system and provide feedback on the quality of its answers. The feedback contains both structured ratings and unstructured natural language explanations. We train a neural model with this feedback data that can generate explanations and re-score answer candidates. We show that feedback data not only improves the accuracy of the deployed QA system but also other stronger non-deployed systems. The generated explanations also help users make informed decisions about the correctness of answers. Project page: https://mcgill-nlp.github.io/feedbackqa/

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). Builds on 23 of its 33 references that are in the map. First posted on arXiv 6 Apr 2022.

Builds on

23 of 33 references.

References · 23

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  3. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
  4. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  5. 2020Learning to summarize from human feedbackcited by 2,562
  6. 2017Reading Wikipedia to Answer Open-Domain Questionscited by 777
  7. 2019Latent Retrieval for Weakly Supervised Open Domain Question Answeringcited by 691
  8. 2018CoQA: A Conversational Question Answering Challengecited by 674
  9. 2020Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?cited by 590
  10. 2018e-SNLI: Natural Language Inference with Natural Language Explanationscited by 468
  11. 2020Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performancecited by 396
  12. 2019Explain Yourself! Leveraging Language Models for Commonsense Reasoningcited by 367
11 more
  1. 2019End-to-End Open-Domain Question Answering with BERTserinicited by 152
  2. 2017ParlAI: A Dialog Research Software Platformcited by 139
  3. 2019Learning from Dialogue after Deployment: Feed Yourself, Chatbot!cited by 102
  4. 2020NILE : Natural Language Inference with Faithful Natural Language Explanationscited by 96
  5. 2020QED: A Framework and Dataset for Explanations in Question Answeringcited by 55
  6. 2016Dialogue Learning With Human-In-The-Loopcited by 46
  7. 2020ExpBERT: Representation Engineering with Natural Language Explanationscited by 28
  8. 2016Dialog-based Language Learningcited by 21
  9. 2019Learning from Explanations with Neural Execution Treecited by 18
  10. 2018Adaptive Document Retrieval for Deep Question Answeringcited by 16
  11. 2020Improving Conversational Question Answering Systems after Deployment using Feedback-Weighted Learningcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 8; 2024: 8; 2025: 3; 2026: 4.

25 papers.

Sort:

By area:

  1. 2023Training Language Models with Language Feedback at Scalecited by 125
  2. 2024Are self-explanations from Large Language Models faithful?cited by 101
  3. 2024RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMscited by 89
  4. 2024Foundational Autoraters: Taming Large Language Models for Better Automatic Evaluationcited by 72
  5. 2024Aligning LLM Agents by Learning Latent Preference from User Editscited by 66
  6. 2023Bridging the Gap: A Survey on Integrating (Human) Feedback for Natural Language Generationcited by 55
  7. 2022Training Language Models with Language Feedbackcited by 48
  8. 2023Learning to Simulate Natural Language Feedback for Interactive Semantic Parsingcited by 19
  9. 2024Black-box Uncertainty Quantification Method for LLM-as-a-Judgecited by 18
  10. 2023Reasons to Reject? Aligning Language Models with Judgmentscited by 15
  11. 2024Position: Towards Bidirectional Human-AI Alignmentcited by 15
  12. 2025Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challengescited by 14
13 more
  1. 2023Continually Improving Extractive QA via Human Feedbackcited by 11
  2. 2026CARE: Confounder-Aware Aggregation for Reliable LLM Evaluationcited by 10
  3. 2023Robust Question Answering against Distribution Shifts with Test-Time Adaptation: An Empirical Studycited by 8
  4. 2024Honesty to Subterfuge: In-Context Reinforcement Learning Can Make Honest Models Reward Hackcited by 8
  5. 2022InterFair: Debiasing with Natural Language Feedback for Fair Interpretable Predictionscited by 7
  6. 2024Reranking Laws for Language Generation: A Communication-Theoretic Perspectivecited by 3
  7. 2023What if you said that differently?: How Explanation Formats Affect Human Feedback Efficacy and User Perceptioncited by 2
  8. 2025Aligning Black-box Language Models with Human Judgmentscited by 1
  9. 2023MWE as WSD: Solving Multiword Expression Identification with Word Sense Disambiguationcited by 0
  10. 2025Multilingual Datasets for Custom Input Extraction and Explanation Requests Parsing in Conversational XAI Systemscited by 0
  11. 2026Modular Expert Merging for Biomedical Retrievalcited by 0
  12. 2026H+ Embedding: Harmonizing Global and Token-Level Retrieval with Context-Dependent Phrasescited by 0
  13. 2026Evidence Lock Before Commitment: A Frozen Interface Degrades LLM-as-Judge Evaluationcited by 0