Challenge: Existing methods for eliciting and calibrating large language models have focused on general reasoning datasets, yielding only modest improvements.
Approach: They propose a method which leverages atypical presentations to adjust model confidence estimates.
Outcome: The proposed method reduces calibration errors by approximately 60% on three medical question answering datasets and outperforms existing methods such as vanilla verbalized confidence, CoT verbalised confidence and others.

Similar Papers

Toward Reliable Clinical Coding with Language Models: Verification and Lightweight Adaptation (2025.emnlp-industry)

Copied to clipboard

Challenge: Existing methods for clinical code verification fail to account for hierarchical misalignments . standardized coding systems such as ICD-10-CM1 ensure consistency across medical records.
Approach: They propose to use prompt engineering and small-scale fine-tuning to improve accuracy without the computational overhead of search-based methods.
Outcome: The proposed task is a standalone task and a pipeline component to address hierarchical near-miss errors without the computational overhead of search-based methods.
DialDefer: A Framework for Detecting and Mitigating LLM Dialogic Deference (2026.acl-long)

Copied to clipboard

Challenge: a single model can shift toward disagreement (skepticism) on graduate-level science and toward agreement (deference) on social judgment.
Approach: They propose a framework to detect and mitigat framing-induced judgment shifts . they propose 'DialDefer' framework to help model disagreements and disagreements based on attribution .
Outcome: The proposed framework detects and mitigates dialogic deference shifts in LLMs . human-vs-LLM attribution drives the largest shifts (17.7 pp swing)
Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback (2023.emnlp-main)

Copied to clipboard

Challenge: Recent studies have shown that unsupervised pre-training produces large language models whose conditional probabilities are remarkably well-calibrated.
Approach: They propose to use verbalized confidences to extract confidence from large language models with reinforcement learning from human feedback to improve their accuracy.
Outcome: The proposed methods reduce the expected calibration error by 50% for RLHF-LMs such as ChatGPT, GPT-4, and Claude.
Format Inertia: A Failure Mechanism of LLMs in Medical Pre-Consultation (2025.emnlp-industry)

Copied to clipboard

Challenge: Recent advances in Large Language Models have brought significant improvements to various service domains, including chatbots and medical pre-consultation applications.
Approach: They propose a method that rebalances the turn-count distribution of training data to mitigate Format Inertia in medical pre-consultation tasks.
Outcome: The proposed method significantly alleviates Format Inertia in medical pre-consultation tasks.
Uncertainty Quantification for Clinical Outcome Predictions with (Large) Language Models (2025.findings-naacl)

Copied to clipboard

Challenge: Language models (LMs) have significant potential for clinical prediction tasks . however, unreliable decisions can result in significant costs due to compromised patient safety and ethical concerns .
Approach: They propose to combine ensembling and multi-tasking approaches to reduce uncertainty in EHRs by using multi-tapping methods.
Outcome: The proposed framework reduces model uncertainty in white-box and black-box settings, and improves model transparency in both settings.
Calibration Meets Explanation: A Simple and Effective Approach for Model Confidence Estimates (2022.emnlp-main)

Copied to clipboard

Challenge: Existing methods to improve confidence calibration of pre-trained language models are still a mystery.
Approach: They propose a method that leverages model explanations to make models less confident with non-inductive attributions.
Outcome: The proposed method improves confidence calibration in all settings and reduces calibration errors when combined with temperature scaling.
Demystifying Uncertainty in LLMs: Active Calibration between Concepts and Human Evaluations (2026.acl-long)

Copied to clipboard

Challenge: Existing static strategies for mitigating hallucinations do not explicitly model the information gain from interacting with the external environment.
Approach: They propose a calibration-driven interactive learning strategy that selects clarification queries by optimizing calibration error.
Outcome: The proposed method provides theoretical guarantees and empirical gains for reliability.
A Comprehensive Survey on the Trustworthiness of Large Language Models in Healthcare (2025.findings-emnlp)

Copied to clipboard

Challenge: a survey of large language models in healthcare raises critical concerns around trustworthiness . trustworthy of LLMs in healthcare remains underexplored, lacking a systematic review .
Approach: a new survey examines the trustworthiness of large language models in healthcare . a review examines how each dimension affects reliability and ethical deployment of LLMs .
Outcome: The present study examines the trustworthiness of large language models in healthcare . it identifies key gaps in existing approaches and challenges posed by evolving paradigms .
Knowing When to Abstain: Medical LLMs Under Clinical Uncertainty (2026.eacl-long)

Copied to clipboard

Challenge: Current evaluation of large language models prioritizes accuracy, but abstention is vital for trustworthy deployment.
Approach: They propose a benchmark and evaluation protocol for abstention in medical multiple-choice question answering . they integrate conformal prediction, adversarial question perturbations, and explicit abstraction options.
Outcome: The proposed protocol improves reliability of medical multiple-choice question answering models by providing explicit abstention options.
Large Language Models Are Overconfident in Their Own Responses (2026.findings-acl)

Copied to clipboard

Challenge: Prior work has shown that instruction-tuned large language models are less well calibrated than their base pre-trained counterparts.
Approach: They propose a simple inference-time strategy that frams the model’s answer as user input during confidence elicitation.
Outcome: The proposed approach reduces overconfidence and improves calibration by up to 26% without retraining.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations