How often do Answers Change? Estimating Recency Requirements in Question Answering

• URL: http://arxiv.org/abs/2603.16544v1
• Date: Tue, 17 Mar 2026 14:07:24 GMT
• Title: How often do Answers Change? Estimating Recency Requirements in Question Answering
• Abstract summary: Large language models (LLMs) often rely on outdated knowledge when answering time-sensitive questions.<n>Existing benchmarks either periodically refresh answers or rely on fixed templates, but they do not reflect on how frequently answers change.<n>We introduce a recency-stationarity taxonomy that categorizes questions by how often their answers change.<n>We present RecencyQA, a dataset of 4,031 open-domain questions annotated with recency and stationarity labels.
• Score: 21.849878234991696
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) often rely on outdated knowledge when answering time-sensitive questions, leading to confident yet incorrect responses. Without explicit signals indicating whether up-to-date information is required, models struggle to decide when to retrieve external evidence, how to reason about stale facts, and how to rank answers by their validity. Existing benchmarks either periodically refresh answers or rely on fixed templates, but they do not reflect on how frequently answers change or whether a question inherently requires up-to-date information. To address this gap, we introduce a recency-stationarity taxonomy that categorizes questions by how often their answers change and whether this change frequency is time-invariant or context-dependent. Building on this taxonomy, we present RecencyQA, a dataset of 4,031 open-domain questions annotated with recency and stationarity labels. Through human evaluation and empirical analysis, we show that non-stationary questions, i.e., those where context changes the recency requirement, are significantly more challenging for LLMs, with difficulty increasing as update frequency rises. By explicitly modeling recency and context dependence, RecencyQA enables fine-grained benchmarking and analysis of temporal reasoning beyond binary notions of freshness, and provides a foundation for developing recency-aware and context-sensitive question answering systems.

Related papers

• It's High Time: A Survey of Temporal Question Answering [17.07150094603319]
  Temporal Question Answering (TQA) focuses on answering questions involving temporal constraints or context.<n>Recent advances in TQA enabled by neural models and Large Language Models (LLMs)<n> benchmark datasets and evaluation strategies designed to test temporal robustness, recency awareness, and generalization.
  arXiv  Detail & Related papers  (2025-05-26T17:21:26Z)
• MRAG: A Modular Retrieval Framework for Time-Sensitive Question Answering [3.117448929160824]
  temporal relations and answering time-sensitive questions is a challenging task for question-answering systems powered by large language models (LLMs)<n>We introduce the TempRAGEval benchmark, which repurposes existing datasets by incorporating temporal perturbations and gold evidence labels.<n>On TempRAGEval, MRAG significantly outperforms baseline retrievers in retrieval performance, leading to further improvements in final answer accuracy.
  arXiv  Detail & Related papers  (2024-12-20T03:58:27Z)
• I Could've Asked That: Reformulating Unanswerable Questions [89.93173151422636]
  We evaluate open-source and proprietary models for reformulating unanswerable questions. GPT-4 and Llama2-7B successfully reformulate questions only 26% and 12% of the time, respectively. We publicly release the benchmark and the code to reproduce the experiments.
  arXiv  Detail & Related papers  (2024-07-24T17:59:07Z)
• CLARINET: Augmenting Language Models to Ask Clarification Questions for Retrieval [52.134133938779776]
  We present CLARINET, a system that asks informative clarification questions by choosing questions whose answers would maximize certainty in the correct candidate. Our approach works by augmenting a large language model (LLM) to condition on a retrieval distribution, finetuning end-to-end to generate the question that would have maximized the rank of the true candidate at each turn.
  arXiv  Detail & Related papers  (2024-04-28T18:21:31Z)
• Answering Ambiguous Questions with a Database of Questions, Answers, and Revisions [95.92276099234344]
  We present a new state-of-the-art for answering ambiguous questions that exploits a database of unambiguous questions generated from Wikipedia. Our method improves performance by 15% on recall measures and 10% on measures which evaluate disambiguating questions from predicted outputs.
  arXiv  Detail & Related papers  (2023-08-16T20:23:16Z)
• RECKONING: Reasoning through Dynamic Knowledge Encoding [51.076603338764706]
  We show that language models can answer questions by reasoning over knowledge provided as part of the context. In these situations, the model fails to distinguish the knowledge that is necessary to answer the question. We propose teaching the model to reason more robustly by folding the provided contextual knowledge into the model's parameters.
  arXiv  Detail & Related papers  (2023-05-10T17:54:51Z)
• RealTime QA: What's the Answer Right Now? [137.04039209995932]
  We introduce REALTIME QA, a dynamic question answering (QA) platform that announces questions and evaluates systems on a regular basis. We build strong baseline models upon large pretrained language models, including GPT-3 and T5. GPT-3 tends to return outdated answers when retrieved documents do not provide sufficient information to find an answer.
  arXiv  Detail & Related papers  (2022-07-27T07:26:01Z)
• SituatedQA: Incorporating Extra-Linguistic Contexts into QA [7.495151447459443]
  We introduce SituatedQA, an open-retrieval QA dataset where systems must produce the correct answer to a question given the temporal or geographical context. We find that a significant proportion of information seeking questions have context-dependent answers. Our study shows that existing models struggle with producing answers that are frequently updated or from uncommon locations.
  arXiv  Detail & Related papers  (2021-09-13T17:53:21Z)
• A Wrong Answer or a Wrong Question? An Intricate Relationship between Question Reformulation and Answer Selection in Conversational Question Answering [15.355557454305776]
  We show that question rewriting (QR) of the conversational context allows to shed more light on this phenomenon. We present the results of this analysis on the TREC CAsT and QuAC (CANARD) datasets.
  arXiv  Detail & Related papers  (2020-10-13T06:29:51Z)
• Understanding Knowledge Gaps in Visual Question Answering: Implications for Gap Identification and Testing [20.117014315684287]
  We use a taxonomy of Knowledge Gaps (KGs) to tag questions with one or more types of KGs. We then examine the skew in the distribution of questions for each KG. These new questions can be added to existing VQA datasets to increase the diversity of questions and reduce the skew.
  arXiv  Detail & Related papers  (2020-04-08T00:27:43Z)
• SQuINTing at VQA Models: Introspecting VQA Models with Sub-Questions [66.86887670416193]
  We show that state-of-the-art VQA models have comparable performance in answering perception and reasoning questions, but suffer from consistency problems. To address this shortcoming, we propose an approach called Sub-Question-aware Network Tuning (SQuINT) We show that SQuINT improves model consistency by 5%, also marginally improving performance on the Reasoning questions in VQA, while also displaying better attention maps.
  arXiv  Detail & Related papers  (2020-01-20T01:02:36Z)

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.