Don't `Well, Actually' Me Unless You Know What You're Talking About: Weak Presupposition Verification Degrades General QA Performance

• URL: http://arxiv.org/abs/2608.06539v1
• Date: Thu, 06 Aug 2026 19:43:10 GMT
• Title: Don't `Well, Actually' Me Unless You Know What You're Talking About: Weak Presupposition Verification Degrades General QA Performance
• Abstract summary: False-presupposition QA (FPQA) tests LLMs on their ability to identify false presuppositions in questions.<n>We show that methods that perform better on FPQs tend to perform worse on TPQs.
• Score: 20.721314515201286
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: False-presupposition QA (FPQA) tests LLMs on their ability to identify false presuppositions in questions and abstain or correct them rather than reinforcing false assumptions. The common approach reduces the task to prompting LLMs to extract presuppositions and fact checking each presupposition. While the performance on dedicated benchmarks keeps improving, evaluation largely focuses on questions with false presuppositions (FPQs) while ignoring the performance on ``normal'' questions (TPQs). Since many benchmarks over-represent FPQs compared to their natural occurrence, the result is that performance on these benchmarks doesn't reflect real-world QA performance. Through extensive experiments across various model families, sizes, and benchmarks, we show that methods that perform better on FPQs tend to perform worse on TPQs. Our analysis reveals this is the result of weak fact checking modules that reject also true presuppositions. We hope our findings will help guide future work toward FPQA methods that generalize well to realistic settings.

Related papers

• LiveFMBench: Unveiling the Power and Limits of Agentic Workflows in Specification Generation [75.05397479715576]
  Large language models (LLMs) and agents have shown promising progress, but their true capabilities and failure modes remain unclear.<n>We present the first systematic and contamination-aware study of LLM- and agent-based formal specification generation for C programs.
  arXiv  Detail & Related papers  (2026-05-02T11:31:33Z)
• Who is the richest club in the championship? Detecting and Rewriting Underspecified Questions Improve QA Performance [6.511402661783843]
  Large language models (LLMs) perform well on well-posed questions, yet standard question-answering (QA) benchmarks remain far from solved.<n>We argue that this gap is partly due to underspecified questions - queries whose interpretation cannot be uniquely determined without additional context.
  arXiv  Detail & Related papers  (2026-02-12T13:36:23Z)
• Benchmarking Uncertainty Calibration in Large Language Model Long-Form Question Answering [7.1559850008795385]
  Large Language Models (LLMs) are commonly used in Question Answering (QA) settings.<n>Existing UQ approaches remain weakly validated in scientific QA.<n>We introduce the first large-scale benchmark for evaluating UQ metrics in reasoning-demanding QA.
  arXiv  Detail & Related papers  (2026-01-30T20:02:34Z)
• The Illusion of Certainty: Uncertainty quantification for LLMs fails under ambiguity [48.899855816199484]
  We introduce MAQA* and AmbigQA*, the first ambiguous question-answering (QA) datasets equipped with ground-truth answer distributions.<n>We show that predictive-distribution and ensemble-based estimators are fundamentally limited under ambiguity.
  arXiv  Detail & Related papers  (2025-11-06T14:46:35Z)
• In-Distribution Consistency Regularization Improves the Generalization of Quantization-Aware Training [16.475151881506914]
  We propose Consistency Regularization (CR) to improve the generalization ability of Quantization-Aware Training (QAT)<n>Our approach significantly outperforms current state-of-the-art QAT methods and even the FP counterparts.
  arXiv  Detail & Related papers  (2024-02-21T03:19:48Z)
• Cofca: A Step-Wise Counterfactual Multi-hop QA benchmark [39.64489055580211]
  We introduce a Step-wise Counterfactual benchmark (CofCA), a novel evaluation benchmark consisting of factual data and counterfactual data. Our experimental results reveal a significant performance gap between Wikipedia-based factual data and counterfactual data, deeming data contamination issues in existing benchmarks.
  arXiv  Detail & Related papers  (2024-02-19T08:12:30Z)
• Self-Evaluation Improves Selective Generation in Large Language Models [54.003992911447696]
  We reformulate open-ended generation tasks into token-level prediction tasks. We instruct an LLM to self-evaluate its answers. We benchmark a range of scoring methods based on self-evaluation.
  arXiv  Detail & Related papers  (2023-12-14T19:09:22Z)
• LLMs as Factual Reasoners: Insights from Existing Benchmarks and Beyond [135.8013388183257]
  We propose a new protocol for inconsistency detection benchmark creation and implement it in a 10-domain benchmark called SummEdits. Most LLMs struggle on SummEdits, with performance close to random chance. The best-performing model, GPT-4, is still 8% below estimated human performance.
  arXiv  Detail & Related papers  (2023-05-23T21:50:06Z)
• Shortcomings of Question Answering Based Factuality Frameworks for Error Localization [51.01957350348377]
  We show that question answering (QA)-based factuality metrics fail to correctly identify error spans in generated summaries. Our analysis reveals a major reason for such poor localization: questions generated by the QG module often inherit errors from non-factual summaries which are then propagated further into downstream modules. Our experiments conclusively show that there exist fundamental issues with localization using the QA framework which cannot be fixed solely by stronger QA and QG models.
  arXiv  Detail & Related papers  (2022-10-13T05:23:38Z)
• Towards Clear Expectations for Uncertainty Estimation [64.20262246029286]
  Uncertainty Quantification (UQ) is crucial to achieve trustworthy Machine Learning (ML) Most UQ methods suffer from disparate and inconsistent evaluation protocols. This opinion paper offers a new perspective by specifying those requirements through five downstream tasks.
  arXiv  Detail & Related papers  (2022-07-27T07:50:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.