Only Say What You Know: Calibration-Aware Generation for Long-Form Factuality

• URL: http://arxiv.org/abs/2605.01749v1
• Date: Sun, 03 May 2026 07:07:09 GMT
• Title: Only Say What You Know: Calibration-Aware Generation for Long-Form Factuality
• Abstract summary: Large Reasoning Models achieve strong performance on complex tasks but remain prone to hallucinations.<n>We propose an textbfExploration-Commitment Decoupling paradigm that disentangles knowledge exploration from final commitment.<n>We instantiate the paradigm with textbfCalibration-Aware Generation (CAG), a framework that equips models with end-to-end, calibration-aware generation capabilities.
• Score: 64.83776302639727
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Reasoning Models achieve strong performance on complex tasks but remain prone to hallucinations, particularly in long-form generation where errors compound across reasoning steps. Existing approaches to improving factuality, including abstention and factuality-driven optimization, follow a \emph{coupled exploration-commitment} paradigm, in which intermediate reasoning is unconditionally propagated to the final output, limiting fine-grained control over information selection and integration. In this paper, we propose an \textbf{Exploration-Commitment Decoupling} paradigm that disentangles knowledge exploration from final commitment, enabling models to explore with awareness while answering cautiously. We instantiate the paradigm with \textbf{Calibration-Aware Generation (CAG)}, a framework that equips models with end-to-end, calibration-aware generation capabilities, by augmenting intermediate reasoning with calibrated reliability estimates and prioritizing reliable content in final outputs. Across five long-form factuality benchmarks and multiple model families, CAG improves factuality by up to 13%, while reducing decoding time by up to 37%. Overall, our work highlights decoupling as a principled approach for more reliable long-form generation, offering directions for trustworthy and self-aware generative systems.

Related papers

• Revitalizing the Beginning: Avoiding Storage Dependency for Model Merging in Continual Learning [57.10440766103372]
  Trajectory Regularized Merging (TRM) is a framework that reformulates the merging phase as an optimization process within an augmented trajectory subspace.<n>Our framework integrates three synergistic objectives including task alignment, prediction consistency, and gradient responsiveness to concurrently preserve merged model's historical stability and re-activate optimization dynamics.
  arXiv  Detail & Related papers  (2026-05-08T14:07:32Z)
• Confidence-Aware Alignment Makes Reasoning LLMs More Reliable [65.44962502963378]
  We introduce CASPO, a framework that aligns token-level confidence with step-wise logical correctness without training a separate reward model.<n>During inference, we propose Confidence-aware Thought (CaT), which dynamically prunes uncertain reasoning branches with negligible O(V) latency.<n>Experiments across ten benchmarks and multiple model families show that CASPO consistently improves reasoning reliability and inference efficiency.
  arXiv  Detail & Related papers  (2026-05-08T07:08:25Z)
• Hit-RAG: Learning to Reason with Long Contexts via Preference Alignment [97.55382322103986]
  Hit-RAG is a multi-stage preference alignment framework designed to resolve cognitive bottlenecks.<n>Our approach systematically refines the utilization of external evidence via three distinct stages.
  arXiv  Detail & Related papers  (2026-03-07T04:05:27Z)
• Reinforcement Inference: Leveraging Uncertainty for Self-Correcting Language Model Reasoning [0.0]
  Reinforcement Inference uses the model's own uncertainty to selectively invoke a second, more deliberate reasoning attempt.<n>On 12,032 MMLU-Pro questions across 14 subjects, using DeepSeek-v3.2 with deterministic decoding in a zero-shot setting, Reinforcement Inference improves accuracy from 60.72% to 84.03%.
  arXiv  Detail & Related papers  (2026-02-09T11:08:24Z)
• ConfSpec: Efficient Step-Level Speculative Reasoning via Confidence-Gated Verification [0.2578242050187029]
  Step-level speculative reasoning aims to mitigate this cost, yet existing approaches face a long-standing trade-off.<n>We propose ConfSpec, a confidence-gated cascaded verification framework that resolves this trade-off.
  arXiv  Detail & Related papers  (2026-01-28T05:58:05Z)
• Deep Self-Evolving Reasoning [22.934253026226155]
  We show that reasoning limits can be substantially extended through a probabilistic paradigm we call Deep Self-Evolving Reasoning (DSER)<n>On the challenging AIME 2024-2025 benchmark, DSER solves 5 out of 9 previously unsolvable problems and boosts overall performance.<n>Our findings establish a clear research agenda for developing next-generation models with powerful, intrinsic self-evolving capabilities.
  arXiv  Detail & Related papers  (2025-10-20T12:51:42Z)
• ConciseHint: Boosting Efficient Reasoning via Continuous Concise Hints during Generation [74.37307916314407]
  We propose a framework dubbed ConciseHint, which continuously encourages the reasoning model to speak concisely.<n>Experiments on the state-of-the-art LRMs, including DeepSeek-R1 and Qwen-3 series, demonstrate that our method can effectively produce concise reasoning.
  arXiv  Detail & Related papers  (2025-06-23T16:20:44Z)
• Enhancing LLM Reliability via Explicit Knowledge Boundary Modeling [41.19330514054401]
  Large language models (LLMs) are prone to hallucination stemming from misaligned self-awareness.<n>We propose the Explicit Knowledge Boundary Modeling framework to integrate fast and slow reasoning systems to harmonize reliability and usability.
  arXiv  Detail & Related papers  (2025-03-04T03:16:02Z)
• Lightweight reranking for language model generations [26.942659041383596]
  We present a novel approach for reranking Large Language Models (LLMs) generations. Unlike other techniques that might involve additional inferences or training a specialized reranker, our approach relies on easy to compute pairwise statistics. We show strong improvements for selecting the best k generations for code generation tasks as well as robust improvements for the best generation for the tasks of autoformalization, summarization, and translation.
  arXiv  Detail & Related papers  (2023-07-11T17:51:48Z)
• Precision-Recall Divergence Optimization for Generative Modeling with GANs and Normalizing Flows [54.050498411883495]
  We develop a novel training method for generative models, such as Generative Adversarial Networks and Normalizing Flows. We show that achieving a specified precision-recall trade-off corresponds to minimizing a unique $f$-divergence from a family we call the textitPR-divergences. Our approach improves the performance of existing state-of-the-art models like BigGAN in terms of either precision or recall when tested on datasets such as ImageNet.
  arXiv  Detail & Related papers  (2023-05-30T10:07:17Z)

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.