# Selective Question Answering under Domain Shift

arXiv: https://arxiv.org/abs/2006.09462 · HTML: https://mlsanity.com/paper/2006.09462/

## Key facts

- Cited by 238 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Jun 2020.

## Built on by (most cited first, 30 of 238)

- [Teaching Models to Express Their Uncertainty in Words](https://mlsanity.com/paper/2205.14334/) (2022)
- [Improving alignment of dialogue agents via targeted human judgements](https://mlsanity.com/paper/2209.14375/) (2022)
- [Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment](https://mlsanity.com/paper/2308.05374/) (2023)
- [Generating with Confidence: Uncertainty Quantification for Black-box Large Language Models](https://mlsanity.com/paper/2305.19187/) (2023)
- [Teaching language models to support answers with verified quotes](https://mlsanity.com/paper/2203.11147/) (2022)
- [A Survey of Confidence Estimation and Calibration in Large Language Models](https://mlsanity.com/paper/2311.08298/) (2023)
- [A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generation](https://mlsanity.com/paper/2307.03987/) (2023)
- [Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaboration](https://mlsanity.com/paper/2402.00367/) (2024)
- [The Unreliability of Explanations in Few-shot Prompting for Textual Reasoning](https://mlsanity.com/paper/2205.03401/) (2022)
- [LM vs LM: Detecting Factual Errors via Cross Examination](https://mlsanity.com/paper/2305.13281/) (2023)
- [Rich Knowledge Sources Bring Complex Knowledge Conflicts: Recalibrating Models to Reflect Conflicting Evidence](https://mlsanity.com/paper/2210.13701/) (2022)
- [Document Understanding Dataset and Evaluation (DUDE)](https://mlsanity.com/paper/2305.08455/) (2023)
- [Know Your Limits: A Survey of Abstention in Large Language Models](https://mlsanity.com/paper/2407.18418/) (2024)
- [Relying on the Unreliable: The Impact of Language Models' Reluctance to Express Uncertainty](https://mlsanity.com/paper/2401.06730/) (2024)
- [The Art of Saying No: Contextual Noncompliance in Language Models](https://mlsanity.com/paper/2407.12043/) (2024)
- [State-of-the-art generalisation research in NLP: A taxonomy and review](https://mlsanity.com/paper/2210.03050/) (2022)
- [Clarify When Necessary: Resolving Ambiguity Through Interaction with LMs](https://mlsanity.com/paper/2311.09469/) (2023)
- [Navigating the Grey Area: How Expressions of Uncertainty and Overconfidence Affect Language Models](https://mlsanity.com/paper/2302.13439/) (2023)
- [Reliable Visual Question Answering: Abstain Rather Than Answer Incorrectly](https://mlsanity.com/paper/2204.13631/) (2022)
- [Can Large Language Models Faithfully Express Their Intrinsic Uncertainty in Words?](https://mlsanity.com/paper/2405.16908/) (2024)
- [Extending the WILDS Benchmark for Unsupervised Adaptation](https://mlsanity.com/paper/2112.05090/) (2021)
- [LUQ: Long-text Uncertainty Quantification for LLMs](https://mlsanity.com/paper/2403.20279/) (2024)
- [Types of Out-of-Distribution Texts and How to Detect Them](https://mlsanity.com/paper/2109.06827/) (2021)
- [On the Relation between Sensitivity and Accuracy in In-context Learning](https://mlsanity.com/paper/2209.07661/) (2022)
- [Break-It-Fix-It: Unsupervised Learning for Program Repair](https://mlsanity.com/paper/2106.06600/) (2021)
- [Revisiting Mahalanobis Distance for Transformer-Based Out-of-Domain Detection](https://mlsanity.com/paper/2101.03778/) (2021)
- [The Art of Defending: A Systematic Evaluation and Analysis of LLM Defense Strategies on Safety and Over-Defensiveness](https://mlsanity.com/paper/2401.00287/) (2023)
- [Learning to Route LLMs with Confidence Tokens](https://mlsanity.com/paper/2410.13284/) (2024)
- [Investigating Selective Prediction Approaches Across Several Tasks in IID, OOD, and Adversarial Settings](https://mlsanity.com/paper/2203.00211/) (2022)
- [Selectively Answering Ambiguous Questions](https://mlsanity.com/paper/2305.14613/) (2023)

## Abstract (arXiv)

To avoid giving wrong answers, question answering (QA) models need to know when to abstain from answering. Moreover, users often ask questions that diverge from the model's training data, making errors more likely and thus abstention more critical. In this work, we propose the setting of selective question answering under domain shift, in which a QA model is tested on a mixture of in-domain and out-of-domain data, and must answer (i.e., not abstain on) as many questions as possible while maintaining high accuracy. Abstention policies based solely on the model's softmax probabilities fare poorly, since models are overconfident on out-of-domain inputs. Instead, we train a calibrator to identify inputs on which the QA model errs, and abstain when it predicts an error is likely. Crucially, the calibrator benefits from observing the model's behavior on out-of-domain data, even if from a different domain than the test data. We combine this method with a SQuAD-trained QA model and evaluate on mixtures of SQuAD and five other QA datasets. Our method answers 56% of questions while maintaining 80% accuracy; in contrast, directly using the model's probabilities only answers 48% at 80% accuracy.