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. |
Similar Papers
Large Language Models are Miscalibrated In-Context Learners (2025.findings-acl)
Copied to clipboard
| Challenge: | In-context Learning and Supervised Fine-Tuning have emerged as pre-dominant methodologies for machine learning and NLP. |
| Approach: | They propose to use self-ensembling to improve both performance and calibration of language models. |
| Outcome: | The proposed learning paradigms can achieve better calibration and better performance than the previous learning paradigm. |
Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback (2023.emnlp-main)
Copied to clipboard
Katherine Tian, Eric Mitchell, Allan Zhou, Archit Sharma, Rafael Rafailov, Huaxiu Yao, Chelsea Finn, Christopher Manning
| 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. |
ADVICE: Answer-Dependent Verbalized Confidence Estimation (2026.acl-long)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) have enabled them to communicate their confidence in natural language, improving transparency and reliability. |
| Approach: | They propose a framework that promotes answer-grounded confidence estimation and analyze the dynamics of verbalized confidence estimation. |
| Outcome: | The proposed framework significantly improves confidence calibration while exhibiting strong generalization to unseen settings without degrading task performance. |
Calibrating the Confidence of Large Language Models by Eliciting Fidelity (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large language models with RLHF and RLAIF have good alignment but exhibit overconfidence post-alignment. |
| Approach: | They propose a plug-and-play method to estimate the confidence of large language models. |
| Outcome: | The proposed method has shown good calibration performance on 6 RLHF-LMs on four MCQA datasets. |
Calibrating Long-form Generations From Large Language Models (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Conventional calibration methods treat answer correctness as binary and do not work for long-form generation where an answer can be partially correct. |
| Approach: | They propose a framework where correctness of LLMs' responses and associated confidence levels are treated as distributions across a range of scores. |
| Outcome: | The proposed framework treats the correctness of the LLMs’ responses and their associated confidence levels as distributions across a range of scores. |
Exploring the Impact of Instruction-Tuning on LLM’s Susceptibility to Misinformation (2025.acl-long)
Copied to clipboard
| Challenge: | Existing studies highlight that large language models are receptive to external information that contradicts their parametric knowledge, but little research has been conducted on the direct impact of instruction-tuning on this phenomenon. |
| Approach: | They examine how instruction-tuning influences LLMs' susceptibility to misinformation, particularly in knowledge conflict situations. |
| Outcome: | The proposed model is more user-oriented and more likely to accept misinformation when it is presented by the user. |
Do Large Language Models Know What They Don’t Know? (2023.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) have vast knowledge that allows them to excel in various NLP tasks. |
| Approach: | They propose an automated method to detect uncertainty in the responses of large language models and a dataset to measure their self-knowledge. |
| Outcome: | The proposed method detects uncertainty in the responses of large language models and provides a novel measure of their self-knowledge. |
Self-Powered LLM Modality Expansion for Large Speech-Text Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large language models exhibit remarkable performance across diverse tasks . however, these methods require significant resource demands and tend to overfit specific tasks. |
| Approach: | They propose a self-powered LSM that leverages augmented automatic speech recognition data generated by the model itself for more effective instruction tuning. |
| Outcome: | The proposed model mitigates speech anchor bias and improves the fusion of speech and text modalities in large language models. |
Conformity in Large Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Conformity is a form of social influence that affects the way people respond to information. |
| Approach: | They adapt psychological experiments to examine the extent of conformity in large language models. |
| Outcome: | The proposed interventions mitigate conformity by reducing the naturalness of majority tones and reducing instruction-tuned models. |
Self-Training Large Language Models with Confident Reasoning (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models generate reasoning paths before final answers, but learning such a path requires costly human supervision. |
| Approach: | They propose a method that fine-tunes LLMs to prefer reasoning paths with high confidence . they propose 'cORE-PO' that fine tunes Lms to choose high-quality reasoning paths . |
| Outcome: | The proposed method improves the accuracy of outputs on four in-distribution and two out-of-difference benchmarks. |