mlsanityData to 7 Oct 2026

Differentiable Conformal Training for LLM Reasoning Factuality

arXiv 2604.20098 ↗First posted 22 Apr 2026cs.LGcited by 1

On the map: LLM reasoning → Test-time compute and efficient thinking

Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning. Builds on 5 of its 26 references that are in the map. First posted on arXiv 22 Apr 2026.

Builds on

5 of 26 references.

Closest ancestors · 1

Same direction, newest first

  1. 2022Language Models (Mostly) Know What They Know11 Jul

Other references · 4

  1. 2023Conformal Language Modelingcited by 163
  2. 2023Conformal Prediction with Large Language Models for Multi-Choice Question Answeringcited by 131
  3. 2024API Is Enough: Conformal Prediction for Large Language Models Without Logit-Accesscited by 68
  4. 2024ConU: Conformal Uncertainty in Large Language Models with Correctness Coverage Guaranteescited by 62

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Uncertainty Quantification for LLM Agents: A Taxonomy, an Evaluation Protocol, and an Empirical Studycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Inference-Time Conformal Reasoning with Valid Factuality Control for Large Language Models
  2. 2026Conditional Factuality Controlled LLMs with Generalization Certificates via Conformal Sampling
  3. 2026Think Through Uncertainty: Improving Long-Form Generation Factuality via Reasoning Calibration
  4. 2026Is Conformal Factuality for RAG-based LLMs Robust? Novel Metrics and Systematic Insights
  5. 2025Probabilistic Soundness Guarantees in LLM Reasoning Chains
  6. 2026Silent Failures in Quantized LLM Reasoning: A Taxonomy-Based Analysis of Hollow Convergence and Failure Mode Shifts
  7. 2025Sample Smart, Not Hard: Correctness-First Decoding for Better Reasoning in LLMs
  8. 2026Double-Calibration: Towards Reliable LLMs via Calibrating Knowledge and Reasoning Confidence