When High Accuracy Hides Poor Calibration: Rethinking Confidence Evaluation in Transformer-Based Text Classification with Balanced Brier Score (2026.acl-long)
Copied to clipboard
Guilherme Fonseca, Gabriel Prenassi, Washington Cunha, Leonardo Chaves Dutra da Rocha, Marcos André Gonçalves
| Challenge: | Existing evidence for TC under fine-tuning is limited. |
| Approach: | They propose a calibration method that balances the contribution of correct and incorrect predictions within confidence bins. |
| Outcome: | The proposed calibration measures show that the models are overconfident even when miscalibrated . the proposed calibration methods challenge calibration assessment practices and provide a more reliable alternative for evaluating confidence quality in Transformer-based TC. |
Similar Papers
Bag of Tricks for In-Distribution Calibration of Pretrained Transformers (2023.findings-eacl)
Copied to clipboard
| Challenge: | Recent studies show that pre-trained language models (PLMs) often predict over-confidently. |
| Approach: | They propose to use ensemble learning and data augmentation to improve confidence calibration for PLMs by combining calibration techniques with a trade-off between accuracy and classification. |
| Outcome: | The proposed calibration method improves classification accuracy and confidence in pre-trained language models by combining several calibration techniques. |
Choose Your Transformer: Improved Transferability Estimation of Transformer Models on Classification Tasks (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing models for NLP tasks require fine-tuning, but it is computationally infeasible. |
| Approach: | They propose an approach that inexpensively estimates a ranking of the expected performance of a given set of transformer language models for a specific task. |
| Outcome: | The proposed model improves the Pearson correlation coefficient between the true model ranks and the estimate. |
On the Effects of Transformer Size on In- and Out-of-Domain Calibration (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Large pre-trained transformer language models are notoriously expensive to train . prior work has developed smaller, more compact models to reduce training costs . |
| Approach: | They propose to develop smaller, more compact transformer language models which can be calibrated in-domain . they show that smaller models can achieve competitive calibration compared to larger models . |
| Outcome: | The proposed models achieve competitive calibration and better calibration than larger models on a wide range of tasks. |
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. |
Calibration of Pre-trained Transformers (2020.emnlp-main)
Copied to clipboard
| Challenge: | Pre-trained Transformers dominate benchmark tasks but use a large number of self-attention heads across many layers in a way that is difficult to unpack. |
| Approach: | They analyze pre-trained Transformer models' posterior probabilities to determine whether they are calibrated for three tasks: natural language inference, paraphrase detection, and commonsense reasoning. |
| Outcome: | The models are calibrated in-domain and out-of-domain, and their calibration error out-domain can be as much as 3.5x lower. |
Insights into LLM Long-Context Failures: When Transformers Know but Don’t Tell (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) exhibit positional bias, struggling to utilize information from the middle or end of long contexts. |
| Approach: | They propose to examine LLMs' long-context generalizations by probing their hidden representations. |
| Outcome: | The proposed models excel at processing extended contexts while preserving their positional bias. |
Towards Objective Fine-tuning: How LLMs’ Prior Knowledge Causes Potential Poor Calibration? (2025.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have enabled powerful domain-specific applications through supervised fine-tuning. |
| Approach: | They propose a cognition-aware framework that applies targeted learning strategies according to the model’s prior knowledge to improve calibration. |
| Outcome: | The proposed framework significantly improves calibration while maintaining performance, achieving an average 57% reduction in ECE compared to standard fine-tuning in Llama3-8B. |
Revisiting Query Variation Robustness of Transformer Models (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Despite their proficiency with natural language, transformer-based large language models are not robust to query variations such as typos and paraphrases. |
| Approach: | They extend their findings to include more recent large language models . they find that instruct-LLMs are more robust to query variations . |
| Outcome: | The proposed model can be prompted for robustness by a set of instruction-tuned LLMs. |
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. |
A Survey of Confidence Estimation and Calibration in Large Language Models (2024.naacl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) have demonstrated impressive capabilities across a wide range of tasks in various domains, but they can be unreliable due to factual errors in their generations. |
| Approach: | They summarize recent advances in LLM confidence estimation and calibration and outline their main lessons learned. |
| Outcome: | The proposed methods can be used to assess the reliability of models and to calibrate them across tasks. |