Differentiable Conformal Training for LLM Reasoning Factuality

• URL: http://arxiv.org/abs/2604.20098v1
• Date: Wed, 22 Apr 2026 01:35:31 GMT
• Title: Differentiable Conformal Training for LLM Reasoning Factuality
• Abstract summary: Large Language Models (LLMs) frequently hallucinate, limiting their reliability in critical applications.<n>Recent work extends Conformal Prediction to filter out risky claims, ensuring that hallucination rates remain below a user-specified level.<n>We introduce Differentiable Coherent Factuality (DCF), a fully differentiable relaxation that enables learning improved scorers while provably recovering the original algorithm's guarantees.
• Score: 6.534904345823168
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) frequently hallucinate, limiting their reliability in critical applications. Conformal Prediction (CP) addresses this by calibrating error rates on held-out data to provide statistically valid confidence guarantees. Recent work extends CP to LLM factuality to filter out risky claims, ensuring that hallucination rates remain below a user-specified level (e.g., 10%). While prior methods treat claims independently, Coherent Factuality extends to multi-step reasoning by representing outputs as dependency graphs and jointly validating claims with their logical ancestors. A key limitation is that Coherent Factuality is not differentiable, requiring hand-crafted scorers that at high reliability levels remove nearly 60% of true claims. We introduce Differentiable Coherent Factuality (DCF), a fully differentiable relaxation that enables learning improved scorers while provably recovering the original algorithm's guarantees. Experiments on two benchmark reasoning datasets demonstrate DCF achieves up to 141% improvement in claim retention while maintaining reliability guarantees, representing a significant step towards reliable conformal LLM systems.

Related papers

• IntroConformal: Conformal Factuality Guarantees for Large Vision-Language Models via Introspective Signals [2.623527845999313]
  We argue that reliable factuality control can be achieved through introspective signals derived from the model itself.<n>IntroConformal is a training-free Conformal Risk Control framework that provides finite-sample, distribution-free factuality guarantees.
  arXiv  Detail & Related papers  (2026-09-01T15:09:56Z)
• CauTion: Knowing When to Trust LLMs for Ensemble Causal Discovery [51.07538881798502]
  Large language models (LLMs) offer a promising source of domain knowledge to complement statistical inference.<n>We propose CauTion, a framework that reliably integrates LLM domain knowledge into an ensemble of statistical causal discovery algorithms.<n>CauTion consistently outperforms both data-centric and LLM-augmented baselines.
  arXiv  Detail & Related papers  (2026-06-02T13:07:43Z)
• Process Supervision of Confidence Margin for Calibrated LLM Reasoning [52.373121066425455]
  Scaling test-time computation with reinforcement learning (RL) has emerged as a reliable path to improve large language models (LLM) reasoning ability.<n>Yet, outcome-based reward often incentivizes models to be overconfident, leading to hallucinations, unreliable confidence-based control, and unnecessary compute allocation.<n>We introduce Reinforcement Learning with Confidence Margin (textbfRLCM), a calibration-aware RL framework that jointly optimize correctness and confidence reliability.
  arXiv  Detail & Related papers  (2026-04-25T14:40:13Z)
• Trust but Verify: Introducing DAVinCI -- A Framework for Dual Attribution and Verification in Claim Inference for Language Models [53.279391576560755]
  Large Language Models (LLMs) have demonstrated remarkable fluency and versatility across a wide range of NLP tasks, yet they remain prone to factual inaccuracies and limitation.<n>This poses significant risks in high-stakes domains such as healthcare, law, and scientific communication, where trust and verifiability are paramount.<n>We introduce DAVinCI - a Dual Attribution and Verification framework designed to enhance the factual reliability and interpretability of LLM outputs.
  arXiv  Detail & Related papers  (2026-04-23T01:37:50Z)
• Think Through Uncertainty: Improving Long-Form Generation Factuality via Reasoning Calibration [7.51755942515969]
  Large language models (LLMs) often hallucinate in long-form generation.<n>Existing approaches mainly improve factuality through post-hoc revision or reinforcement learning.<n>We propose CURE, a framework that improves long-form factuality by teaching LLMs to reason about uncertainty at the claim level.
  arXiv  Detail & Related papers  (2026-04-13T20:38:36Z)
• Less Approximates More: Harmonizing Performance and Confidence Faithfulness via Hybrid Post-Training for High-Stakes Tasks [52.81286869496811]
  Large language models are increasingly deployed in high-stakes tasks, where confident yet incorrect inferences may cause real-world harm.<n>We propose to jointly optimize unsupervised Reinforcement Learning from Internal Feedback with reasoning-trace-guided Reasoning Distillation.<n>We introduce HyTuning, a hybrid post-training framework that adaptively reweights RD and RLIF via a PRG-style metric.
  arXiv  Detail & Related papers  (2026-04-09T16:50:11Z)
• Is Conformal Factuality for RAG-based LLMs Robust? Novel Metrics and Systematic Insights [7.594584500009769]
  Large language models (LLMs) frequently hallucinate, limiting their reliability in knowledge-intensive applications.<n>Retrieval-augmented generation (RAG) and conformal factuality have emerged as potential ways to address this limitation.<n>We analyze the reliability and usefulness of conformal factuality for RAG-based LLMs across generation, scoring, calibration, robustness, and efficiency.
  arXiv  Detail & Related papers  (2026-03-17T17:20:08Z)
• Confidence Before Answering: A Paradigm Shift for Efficient LLM Uncertainty Estimation [47.91529693614168]
  Existing methods are predominantly answer-first, producing confidence only after generating an answer.<n>We study a confidence-first paradigm, where the model outputs its confidence before answering, interpreting this score as the model's probability of answering the question correctly.<n>We propose CoCA, a reinforcement learning framework that jointly optimize confidence calibration and answer accuracy via segmented credit assignment.
  arXiv  Detail & Related papers  (2026-03-06T04:03:13Z)
• VI-CuRL: Stabilizing Verifier-Independent RL Reasoning via Confidence-Guided Variance Reduction [55.04308051033549]
  Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a dominant paradigm for enhancing Large Language Models (LLMs) reasoning.<n>We introduceVerifier-Independent Curriculum Reinforcement Learning (VI-CuRL), a framework that leverages the model's intrinsic confidence to construct a curriculum independent from external verifiers.
  arXiv  Detail & Related papers  (2026-02-13T03:40:52Z)
• Towards Comprehensive Stage-wise Benchmarking of Large Language Models in Fact-Checking [64.97768177044355]
  Large Language Models (LLMs) are increasingly deployed in real-world fact-checking systems.<n>We present FactArena, a fully automated arena-style evaluation framework.<n>Our analyses reveal significant discrepancies between static claim-verification accuracy and end-to-end fact-checking competence.
  arXiv  Detail & Related papers  (2026-01-06T02:51:56Z)
• Fact-Checking with Large Language Models via Probabilistic Certainty and Consistency [7.806516365113592]
  Large language models (LLMs) are increasingly used in applications requiring factual accuracy.<n>While fact-checking can mitigate these errors, existing methods typically retrieve external evidence indiscriminately.<n>We introduce Probabilistic Certainty and Consistency (PCC), a framework that estimates factual confidence.
  arXiv  Detail & Related papers  (2026-01-05T21:57:41Z)
• Robust Uncertainty Quantification for Self-Evolving Large Language Models via Continual Domain Pretraining [7.344577590113121]
  Conformal Prediction (CP) has shown promise in offering correctness guarantees for large language models.<n>We introduce an adaptive rejection and non-exchangeable CP framework.<n>Our framework enhances both the effectiveness and reliability of CP under CDP scenarios.
  arXiv  Detail & Related papers  (2025-10-27T02:15:51Z)
• COIN: Uncertainty-Guarding Selective Question Answering for Foundation Models with Provable Risk Guarantees [51.5976496056012]
  COIN is an uncertainty-guarding selection framework that calibrates statistically valid thresholds to filter a single generated answer per question.<n>COIN estimates the empirical error rate on a calibration set and applies confidence interval methods to establish a high-probability upper bound on the true error rate.<n>We demonstrate COIN's robustness in risk control, strong test-time power in retaining admissible answers, and predictive efficiency under limited calibration data.
  arXiv  Detail & Related papers  (2025-06-25T07:04:49Z)
• Aligning Large Language Models for Faithful Integrity Against Opposing Argument [71.33552795870544]
  Large Language Models (LLMs) have demonstrated impressive capabilities in complex reasoning tasks.<n>They can be easily misled by unfaithful arguments during conversations, even when their original statements are correct.<n>We propose a novel framework, named Alignment for Faithful Integrity with Confidence Estimation.
  arXiv  Detail & Related papers  (2025-01-02T16:38:21Z)

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.