# Confidence Estimation for LLMs in Multi-turn Interactions

arXiv: https://arxiv.org/abs/2601.02179 · HTML: https://mlsanity.com/paper/2601.02179/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 28 references that are in the map.
- First posted on arXiv 5 Jan 2026.

## Builds on (most cited first, 23 of 23)

- [Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs](https://mlsanity.com/paper/2306.13063/) (2023)
- [Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback](https://mlsanity.com/paper/2305.14975/) (2023)
- [LLMs Get Lost In Multi-Turn Conversation](https://mlsanity.com/paper/2505.06120/) (2025)
- [MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback](https://mlsanity.com/paper/2309.10691/) (2023)
- [A Survey of Confidence Estimation and Calibration in Large Language Models](https://mlsanity.com/paper/2311.08298/) (2023)
- [MT-Bench-101: A Fine-Grained Benchmark for Evaluating Large Language Models in Multi-Turn Dialogues](https://mlsanity.com/paper/2402.14762/) (2024)
- [A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systems](https://mlsanity.com/paper/2402.18013/) (2024)
- [Can LLM be a Personalized Judge?](https://mlsanity.com/paper/2406.11657/) (2024)
- [LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models](https://mlsanity.com/paper/2311.18232/) (2023)
- [LUQ: Long-text Uncertainty Quantification for LLMs](https://mlsanity.com/paper/2403.20279/) (2024)
- [BotChat: Evaluating LLMs' Capabilities of Having Multi-Turn Dialogues](https://mlsanity.com/paper/2310.13650/) (2023)
- [Conformity in Large Language Models](https://mlsanity.com/paper/2410.12428/) (2024)
- [Atomic Calibration of LLMs in Long-Form Generations](https://mlsanity.com/paper/2410.13246/) (2024)
- [CoT-UQ: Improving Response-wise Uncertainty Quantification in LLMs with Chain-of-Thought](https://mlsanity.com/paper/2502.17214/) (2025)
- [A Head to Predict and a Head to Question: Pre-trained Uncertainty Quantification Heads for Hallucination Detection in LLM Outputs](https://mlsanity.com/paper/2505.08200/) (2025)
- [LoGU: Long-form Generation with Uncertainty Expressions](https://mlsanity.com/paper/2410.14309/) (2024)
- [LoVeC: Reinforcement Learning for Better Verbalized Confidence in Long-Form Generations](https://mlsanity.com/paper/2505.23912/) (2025)
- [Do We Need Language-Specific Fact-Checking Models? The Case of Chinese](https://mlsanity.com/paper/2401.15498/) (2024)
- [UNCLE: Benchmarking Uncertainty Expressions in Long-Form Generation](https://mlsanity.com/paper/2505.16922/) (2025)
- [Beyond the Final Layer: Intermediate Representations for Better Multilingual Calibration in Large Language Models](https://mlsanity.com/paper/2510.03136/) (2025)
- [Navigating the Alignment-Calibration Trade-off: A Pareto-Superior Frontier via Model Merging](https://mlsanity.com/paper/2510.17426/) (2025)
- [GRACE: A Granular Benchmark for Evaluating Model Calibration against Human Calibration](https://mlsanity.com/paper/2502.19684/) (2025)
- [All Roads Lead to Rome: Graph-Based Confidence Estimation for Large Language Model Reasoning](https://mlsanity.com/paper/2509.12908/) (2025)

## Built on by (most cited first, 12 of 12)

- [Uncertainty Quantification in LLM Agents: Foundations, Emerging Challenges, and Opportunities](https://mlsanity.com/paper/2602.05073/) (2026)
- [Demystifying Multi-Agent Debate: The Role of Confidence and Diversity](https://mlsanity.com/paper/2601.19921/) (2026)
- [Value of Information: A Framework for Human-Agent Communication](https://mlsanity.com/paper/2601.06407/) (2026)
- [Thinking by Subtraction: Confidence-Driven Contrastive Decoding for LLM Reasoning](https://mlsanity.com/paper/2602.18232/) (2026)
- [A Systematic Evaluation of Black-Box Uncertainty Estimation Methods for Large Language Models](https://mlsanity.com/paper/2606.19868/) (2026)
- [When Calibration Rankings Reverse: Accuracy-Controlled Evaluation for Fair Comparison of LLMs](https://mlsanity.com/paper/2606.30814/) (2026)
- [Quantitative Introspection in Language Models: Tracking Emotive States Across Conversation](https://mlsanity.com/paper/2603.18893/) (2026)
- [Confidence Should Be Calibrated More Than One Turn Deep](https://mlsanity.com/paper/2604.05397/) (2026)
- [Beyond Single-Turn Confidence: Trajectory-Adapted Uncertainty Quantification for LLM Agents](https://mlsanity.com/paper/2608.11552/) (2026)
- [From Sequence to Structure: Relational Uncertainty Propagation for LLM Agents](https://mlsanity.com/paper/2608.16002/) (2026)
- [Uncertainty Quantification for LLM Agents: A Taxonomy, an Evaluation Protocol, and an Empirical Study](https://mlsanity.com/paper/2609.07395/) (2026)
- [GRUET: Quantifying Uncertainty of Agentic Reasoning-and-Acting Processes](https://mlsanity.com/paper/2609.24831/) (2026)

## Abstract (arXiv)

While confidence estimation is a promising direction for mitigating hallucinations in Large Language Models (LLMs), current research overwhelmingly focuses on single-turn settings. The dynamics of model confidence in multi-turn conversations, where context accumulates and ambiguity is progressively resolved, remain largely unexplored. This work presents the first systematic study of confidence estimation in multi-turn interactions, establishing a formal evaluation framework grounded in two key desiderata: per-turn calibration and monotonicity of confidence as more information becomes available. To facilitate this, we introduce novel metrics, including a length-normalized Expected Calibration Error (InfoECE), and a new "Hinter-Guesser" paradigm for generating controlled evaluation datasets. Our experiments reveal that widely-used confidence techniques struggle with calibration and monotonicity in multi-turn dialogues. In contrast, a novel logit-based probe we introduce, P(Sufficient), proves comparatively more effective, robustly tracking evidence accumulation and distinguishing it from conversational filler. Our work provides a foundational methodology for developing more reliable and trustworthy conversational agents.