When Silence Is Golden: Can LLMs Learn to Abstain in Temporal QA and Beyond?

• URL: http://arxiv.org/abs/2602.04755v1
• Date: Wed, 04 Feb 2026 16:54:47 GMT
• Title: When Silence Is Golden: Can LLMs Learn to Abstain in Temporal QA and Beyond?
• Abstract summary: Large language models (LLMs) rarely admit uncertainty, often producing fluent but misleading answers, rather than abstaining (i.e., refusing to answer)<n>This weakness is even evident in temporal question answering, where models frequently ignore time-sensitive evidence and facts across different time-periods.<n>Existing approaches such as calibration might be unreliable in capturing uncertainty in complex reasoning.<n>We frame abstention as a teachable skill and introduce a pipeline that couples Chain-of-Thought (CoT) supervision with Reinforcement Learning (RL) guided by abstention-aware rewards.
• Score: 34.471723373734605
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Large language models (LLMs) rarely admit uncertainty, often producing fluent but misleading answers, rather than abstaining (i.e., refusing to answer). This weakness is even evident in temporal question answering, where models frequently ignore time-sensitive evidence and conflate facts across different time-periods. In this paper, we present the first empirical study of training LLMs with an abstention ability while reasoning about temporal QA. Existing approaches such as calibration might be unreliable in capturing uncertainty in complex reasoning. We instead frame abstention as a teachable skill and introduce a pipeline that couples Chain-of-Thought (CoT) supervision with Reinforcement Learning (RL) guided by abstention-aware rewards. Our goal is to systematically analyze how different information types and training techniques affect temporal reasoning with abstention behavior in LLMs. Through extensive experiments studying various methods, we find that RL yields strong empirical gains on reasoning: a model initialized by Qwen2.5-1.5B-Instruct surpasses GPT-4o by $3.46\%$ and $5.80\%$ in Exact Match on TimeQA-Easy and Hard, respectively. Moreover, it improves the True Positive rate on unanswerable questions by $20\%$ over a pure supervised fine-tuned (SFT) variant. Beyond performance, our analysis shows that SFT induces overconfidence and harms reliability, while RL improves prediction accuracy but exhibits similar risks. Finally, by comparing implicit reasoning cues (e.g., original context, temporal sub-context, knowledge graphs) with explicit CoT supervision, we find that implicit information provides limited benefit for reasoning with abstention. Our study provides new insights into how abstention and reasoning can be jointly optimized, providing a foundation for building more reliable LLMs.

Related papers

• Enhancing LLM Metacognition via Cognitive Pairwise Training [56.19495984013656]
  Reinforcement learning with verifiable rewards can make models more willing to give confident answers when evidence or reasoning is unreliable.<n>Existing SFT or RL methods mainly teach LLMs to refuse or express uncertainty at the response level.<n>We propose Cognitive Pairwise Training (CPT), a cognitive mid-training alignment stage that turns pairwise comparisons over reasoning traces into a reusable alignment signal.
  arXiv  Detail & Related papers  (2026-05-30T19:53:19Z)
• Teaching Large Language Models When Not to Know: Learning Temporal Critique for Ex-Ante Reasoning [21.280999165642932]
  Large language models (LLMs) often fail to reason under temporal cutoffs.<n>We propose TCFT, a framework that trains models to acquire cutoff-aware temporal verification.
  arXiv  Detail & Related papers  (2026-05-14T09:49:35Z)
• Beyond Reasoning: Reinforcement Learning Unlocks Parametric Knowledge in LLMs [59.62441340813425]
  We study whether reinforcement learning can improve direct recall of parametric knowledge.<n>Across three model families and multiple factual QA benchmarks, RL yields 27% average relative gains.<n>Mechanistically, RL primarily redistributes probability mass over existing knowledge rather than acquiring new facts.
  arXiv  Detail & Related papers  (2026-05-08T02:40:12Z)
• Balancing Faithfulness and Performance in Reasoning via Multi-Listener Soft Execution [79.98699884805636]
  Reasoning Execution by Multiple Listeners (REMUL) is a multi-party reinforcement learning approach.<n>REMUL builds on the hypothesis that reasoning traces which other parties can follow will be more faithful.<n>Speakers are rewarded for producing reasoning that is clear to listeners.
  arXiv  Detail & Related papers  (2026-02-18T02:55:55Z)
• Are Reasoning LLMs Robust to Interventions on Their Chain-of-Thought? [79.86483056611105]
  Reasoning LLMs generate step-by-step chains of thought before giving an answer.<n>How robust are these reasoning traces to disruptions that occur within them?<n>We introduce a controlled evaluation framework that perturbs a model's own CoT at fixed timesteps.
  arXiv  Detail & Related papers  (2026-02-07T10:02:58Z)
• Can Confidence Estimates Decide When Chain-of-Thought Is Necessary for LLMs? [32.02698064940949]
  Chain-of-thought (CoT) prompting has emerged as a common technique for enhancing the reasoning abilities of large language models.<n>We present the first systematic study of training-free confidence estimation methods for CoT gating.
  arXiv  Detail & Related papers  (2025-10-23T21:33:28Z)
• Bridging Supervised Learning and Reinforcement Learning in Math Reasoning [55.889740979706815]
  Reinforcement Learning (RL) has played a central role in the recent surge of math abilities by enabling self-improvement through binary verifier signals.<n>In this work, we propose Negative-aware Fine-Tuning (NFT) -- a supervised approach that enables LLMs to reflect on their failures and improve autonomously with no external teachers.
  arXiv  Detail & Related papers  (2025-05-23T17:17:40Z)
• Right Question is Already Half the Answer: Fully Unsupervised LLM Reasoning Incentivization [47.04132451658664]
  ours achieves competitive performance compared to supervised counterparts on both mathematical and free-form natural reasoning tasks.<n>Without any supervised signals, ours boosts the accuracy of Qwen2.5-Math-7B Base from 30.7% to 48.1% on mathematical benchmarks.
  arXiv  Detail & Related papers  (2025-04-08T08:48:51Z)
• Concise Reasoning via Reinforcement Learning [13.657506042120167]
  We revisit the core principles of reinforcement learning (RL)<n>We uncover a natural correlation between conciseness and accuracy that has been largely overlooked.<n>We show that introducing a secondary phase of RL training, using a very small set of problems, can significantly reduce chains of thought.
  arXiv  Detail & Related papers  (2025-04-07T15:35:54Z)
• Video SimpleQA: Towards Factuality Evaluation in Large Video Language Models [77.96693360763925]
  Video SimpleQA is the first comprehensive benchmark tailored for factuality evaluation in video contexts.<n>Our work differs from existing video benchmarks through the following key features: Knowledge required: demanding integration of external knowledge beyond the video's explicit narrative.<n>Short-form definitive answer: Answers are crafted as unambiguous and definitively correct in a short format with minimal scoring variance.
  arXiv  Detail & Related papers  (2025-03-24T17:46:09Z)
• Balancing Truthfulness and Informativeness with Uncertainty-Aware Instruction Fine-Tuning [79.48839334040197]
  Instruction fine-tuning (IFT) can increase the informativeness of large language models (LLMs), but may reduce their truthfulness.<n>In this paper, we empirically demonstrate how unfamiliar knowledge in IFT datasets can negatively affect the truthfulness of LLMs.<n>We introduce two new IFT paradigms, $UNIT_cut$ and $UNIT_ref$, to address this issue.
  arXiv  Detail & Related papers  (2025-02-17T16:10:30Z)
• Living in the Moment: Can Large Language Models Grasp Co-Temporal Reasoning? [70.19200858203388]
  Temporal reasoning is fundamental for large language models to comprehend the world. CoTempQA is a benchmark containing four co-temporal scenarios. Our experiments reveal a significant gap between the performance of current LLMs and human-level reasoning.
  arXiv  Detail & Related papers  (2024-06-13T12:56:21Z)
• Uncertainty Quantification for In-Context Learning of Large Language Models [52.891205009620364]
  In-context learning has emerged as a groundbreaking ability of Large Language Models (LLMs) We propose a novel formulation and corresponding estimation method to quantify both types of uncertainties. The proposed method offers an unsupervised way to understand the prediction of in-context learning in a plug-and-play fashion.
  arXiv  Detail & Related papers  (2024-02-15T18:46:24Z)
• Temporal Knowledge Question Answering via Abstract Reasoning Induction [32.08799860090592]
  This study addresses the challenge of enhancing temporal knowledge reasoning in Large Language Models (LLMs) We propose Abstract Reasoning Induction (ARI) framework, which divides temporal reasoning into two distinct phases: Knowledge-agnostic and Knowledge-based. Our approach achieves remarkable improvements, with relative gains of 29.7% and 9.27% on two temporal QA datasets.
  arXiv  Detail & Related papers  (2023-11-15T17:46:39Z)

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.