EMNLP Findings2025
Adaptive Platt Scaling with Causal Interpretations for Self-Reflective Language Model Uncertainty Estimates
Anthony Sicilia, Malihe Alikhani
Abstract
As large language models (LLMs) are consumed by more users and deployed in increasingly autonomous capacities, their ability to self-monitor and ask for human intervention is of vital importance. Underlying this capability are fundamental skills like self-reflection and expression of uncertainty. In this work, we provide a formal analysis of LLM self-reflection for uncertainty estimation, using domain adaptation theory to model the shift between base predictions and reflective judgments. We use this to motivate a temperature scaling algorithm that calibrates uncertainty using comparisons between base predictions and LLM self-reflections. We evaluate our approach on challenging question-answering tasks requiring reasoning, demonstrating that our methods can improve calibration of uncertainty estimates and also offer improvements in human interpretation. More broadly, this use case shows how domain adaptation presents a promising analytical tool for understanding the underlying statistical properties of LLM self-reflections.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- Reflexion: language agents with verbal reinforcement learning cites Self-Refine: Iterative Refinement with Self-Feedback
- CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing cites Self-Refine: Iterative Refinement with Self-Feedback
Builds on13
- Measuring Massive Multitask Language UnderstandingDan Hendrycks, Collin Burns, Steven Basart, Andy Zou et al.ICLR 2021 · 7,905 citations
- Reflexion: language agents with verbal reinforcement learningNoah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan et al.NeurIPS 2023 · 5,828 citations
- Self-Refine: Iterative Refinement with Self-FeedbackAman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan et al.NeurIPS 2023 · 4,972 citations
- CRITIC: Large Language Models Can Self-Correct with Tool-Interactive CritiquingZhibin Gou, Zhihong Shao, Yeyun Gong, Yelong Shen et al.ICLR 2024 · 699 citations
- The Metacognitive Demands and Opportunities of Generative AILev Tankelevitch, Viktor Kewenig, Auste Simkute, Ava Elizabeth Scott et al.CHI 2024 · 279 citations
Related papers
- SelfReflect: Can LLMs Communicate Their Internal Answer Distribution?Michael Kirchhof, Luca Füger, Adam Golinski, Eeshan Gunesh Dhekane et al.ICLR 2026 · 4 citations
- Rewarding Doubt: A Reinforcement Learning Approach to Calibrated Confidence Expression of Large Language ModelsDavid Bani-Harouni, Chantal Pellegrini, Paul Stangel, Ege Özsoy et al.ICLR 2026 · 49 citations
- SaySelf: Teaching LLMs to Express Confidence with Self-Reflective RationalesTianyang Xu, Shujin Wu, Shizhe Diao, Xiaoze Liu et al.EMNLP 2024 · 10 citations
- MetaFaith: Faithful Natural Language Uncertainty Expression in LLMsGabrielle Kaili-May Liu, Gal Yona, Avi Caciularu, Idan Szpektor et al.EMNLP 2025
- Learning to Route LLMs with Confidence TokensYu-Neng Chuang, Prathusha Kameswara Sarma, Parikshit Gopalan, John Boccio et al.ICML 2025
