Related papers: MICE for CATs: Model-Internal Confidence Estimatio…

Large Language Models (LLMs) are increasingly applied in high-stakes domains such as finance, healthcare, and education, where reliable multi-turn interactions with users are essential. However, existing work on confidence estimation and…

Assessing the reliability of Large Language Models (LLMs) by confidence elicitation is a prominent approach to AI safety in high-stakes applications, such as healthcare and finance. Existing methods either require expensive computational…

To be considered reliable, a model must be calibrated so that its confidence in each decision closely reflects its true outcome. In this blogpost we'll take a look at the most commonly used definition for calibration and then dive into a…

As probabilistic models continue to permeate various facets of our society and contribute to scientific advancements, it becomes a necessity to go beyond traditional metrics such as predictive accuracy and error rates and assess their…

Despite widespread adoption, machine learning models remain mostly black boxes. Understanding the reasons behind predictions is, however, quite important in assessing trust, which is fundamental if one plans to take action based on a…

Language models are often miscalibrated, leading to confidently incorrect answers. We introduce GRACE, a benchmark for language model calibration that incorporates comparison with human calibration. GRACE consists of question-answer pairs,…

Pre-trained language models (PLMs) serve as backbones for various real-world systems. For high-stake applications, it's equally essential to have reasonable confidence estimations in predictions. While the vanilla confidence scores of PLMs…

Calibration measures whether a model's predicted confidence aligns with its empirical accuracy, and is central to the reliable deployment of large language models (LLMs) in high-stakes domains such as medicine and law. While much recent…

This paper presents a new Python library called Automated Learning for Insightful Comparison and Evaluation (ALICE), which merges conventional feature selection and the concept of inter-rater agreeability in a simple, user-friendly manner…

Confidence estimation (CE) indicates how reliable the answers of large language models are and impacts user trust and decision-making. Existing evaluations mainly concern the alignment between confidence and correctness, but ignore the…

Multiple classifier system (MCS) has become a successful alternative for improving classification performance. However, studies have shown inconsistent results for different MCSs, and it is often difficult to predict which MCS algorithm…

Evaluating whether explanations faithfully reflect a model's reasoning remains an open problem. Existing benchmarks use single interventions without statistical testing, making it impossible to distinguish genuine faithfulness from…

Recent advancements in the field of natural language generation have facilitated the use of large language models to assess the quality of generated text. Although these models have shown promising results in tasks such as machine…

This paper proposes a new metric to measure the calibration error of probabilistic binary classifiers, called test-based calibration error (TCE). TCE incorporates a novel loss function based on a statistical test to examine the extent to…

Analyzing classification model performance is a crucial task for machine learning practitioners. While practitioners often use count-based metrics derived from confusion matrices, like accuracy, many applications, such as weather…

LLMs' linguistically expressed confidence should faithfully reflect their intrinsic uncertainty. While recent work shows LLMs struggle to use epistemic markers (e.g., "it is likely...") in a human-aligned fashion, it remains unclear whether…

Psychology research has shown that humans are poor at estimating their performance on tasks, tending towards underconfidence on easy tasks and overconfidence on difficult tasks. We examine three LLMs, Llama-3-70B-instruct, Claude-3-Sonnet,…

Confidence calibration, which aims to make model predictions equal to the true correctness measures, is important for neural machine translation (NMT) because it is able to offer useful indicators of translation errors in the generated…

When a model knows when it does not know, many possibilities emerge. The first question is how to enable a model to recognize that it does not know. A promising approach is to use confidence, computed from the model's internal signals, to…

Confidence calibration is essential for making large language models (LLMs) reliable, yet existing training-free methods have been primarily studied under single-answer question answering. In this paper, we show that these methods break…