UQ: Assessing Language Models on Unsolved Questions

• URL: http://arxiv.org/abs/2508.17580v1
• Date: Mon, 25 Aug 2025 01:07:59 GMT
• Title: UQ: Assessing Language Models on Unsolved Questions
• Authors: Fan Nie, Ken Ziyu Liu, Zihao Wang, Rui Sun, Wei Liu, Weijia Shi, Huaxiu Yao, Linjun Zhang, Andrew Y. Ng, James Zou, Sanmi Koyejo, Yejin Choi, Percy Liang, Niklas Muennighoff,
• Abstract summary: We introduce UQ, a testbed of 500 challenging, diverse questions sourced from Stack Exchange.<n>UQ is difficult and realistic by construction: unsolved questions are often hard and naturally arise when humans seek answers.<n>The top model passes UQ-validation on only 15% of questions, and preliminary human verification has already identified correct answers.
• Score: 149.46593270027697
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Benchmarks shape progress in AI research. A useful benchmark should be both difficult and realistic: questions should challenge frontier models while also reflecting real-world usage. Yet, current paradigms face a difficulty-realism tension: exam-style benchmarks are often made artificially difficult with limited real-world value, while benchmarks based on real user interaction often skew toward easy, high-frequency problems. In this work, we explore a radically different paradigm: assessing models on unsolved questions. Rather than a static benchmark scored once, we curate unsolved questions and evaluate models asynchronously over time with validator-assisted screening and community verification. We introduce UQ, a testbed of 500 challenging, diverse questions sourced from Stack Exchange, spanning topics from CS theory and math to sci-fi and history, probing capabilities including reasoning, factuality, and browsing. UQ is difficult and realistic by construction: unsolved questions are often hard and naturally arise when humans seek answers, thus solving them yields direct real-world value. Our contributions are threefold: (1) UQ-Dataset and its collection pipeline combining rule-based filters, LLM judges, and human review to ensure question quality (e.g., well-defined and difficult); (2) UQ-Validators, compound validation strategies that leverage the generator-validator gap to provide evaluation signals and pre-screen candidate solutions for human review; and (3) UQ-Platform, an open platform where experts collectively verify questions and solutions. The top model passes UQ-validation on only 15% of questions, and preliminary human verification has already identified correct answers among those that passed. UQ charts a path for evaluating frontier models on real-world, open-ended challenges, where success pushes the frontier of human knowledge. We release UQ at https://uq.stanford.edu.

Related papers

• Inferential Question Answering [67.54465021408724]
  We introduce Inferential QA -- a new task that challenges models to infer answers from answer-supporting passages which provide only clues.<n>To study this problem, we construct QUIT (QUestions requiring Inference from Texts) dataset, comprising 7,401 questions and 2.4M passages.<n>We show that methods effective on traditional QA tasks struggle in inferential QA: retrievers underperform, rerankers offer limited gains, and fine-tuning provides inconsistent improvements.
  arXiv  Detail & Related papers  (2026-02-01T14:02:43Z)
• 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)
• Self-Questioning Language Models [51.75087358141567]
  We propose an asymmetric self-play framework where a proposer is given the topic and generates a question for a solver.<n>Both the proposer and solver are trained via reinforcement learning.<n>We study this asymmetric self-play framework on three benchmarks: three-digit multiplication, algebra problems from the OMEGA benchmark, and programming problems from Codeforces.
  arXiv  Detail & Related papers  (2025-08-05T17:51:33Z)
• Reliable and Efficient Amortized Model-based Evaluation [57.6469531082784]
  The average score across a wide range of benchmarks provides a signal that helps guide the use of language models in practice.<n>A popular attempt to lower the cost is to compute the average score on a subset of the benchmark.<n>This approach often renders an unreliable measure of LM performance because the average score is often confounded with the difficulty of the questions in the benchmark subset.<n>We train a model that predicts question difficulty from its content, enabling a reliable measurement at a fraction of the cost.
  arXiv  Detail & Related papers  (2025-03-17T16:15:02Z)
• Wrong Answers Can Also Be Useful: PlausibleQA -- A Large-Scale QA Dataset with Answer Plausibility Scores [16.434748534272014]
  PlausibleQA is a dataset of 10,000 questions and 100,000 candidate answers annotated with plausibility scores and justifications.<n>We show that plausibility-aware approaches are effective for Multiple-Choice Question Answering (MCQA) and QARA.
  arXiv  Detail & Related papers  (2025-02-22T21:14:18Z)
• Toward Unsupervised Realistic Visual Question Answering [70.67698100148414]
  We study the problem of realistic VQA (RVQA), where a model has to reject unanswerable questions (UQs) and answer answerable ones (AQs) We first point out 2 drawbacks in current RVQA research, where (1) datasets contain too many unchallenging UQs and (2) a large number of annotated UQs are required for training. We propose a new testing dataset, RGQA, which combines AQs from an existing VQA dataset with around 29K human-annotated UQs. This combines pseudo UQs obtained by randomly pairing images and questions, with an
  arXiv  Detail & Related papers  (2023-03-09T06:58:29Z)
• Improving Unsupervised Question Answering via Summarization-Informed Question Generation [47.96911338198302]
  Question Generation (QG) is the task of generating a plausible question for a passage, answer> pair. We make use of freely available news summary data, transforming declarative sentences into appropriate questions using dependency parsing, named entity recognition and semantic role labeling. The resulting questions are then combined with the original news articles to train an end-to-end neural QG model.
  arXiv  Detail & Related papers  (2021-09-16T13:08:43Z)
• ProtoQA: A Question Answering Dataset for Prototypical Common-Sense Reasoning [35.6375880208001]
  This paper introduces a new question answering dataset for training and evaluating common sense reasoning capabilities of artificial intelligence systems. The training set is gathered from an existing set of questions played in a long-running international game show FAMILY- FEUD. We also propose a generative evaluation task where a model has to output a ranked list of answers, ideally covering prototypical answers for a question.
  arXiv  Detail & Related papers  (2020-05-02T09:40:05Z)

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.