Related papers: Calibration Is Not Enough: Evaluating Confidence E…

Native speakers can judge whether a sentence is an acceptable instance of their language. Acceptability provides a means of evaluating whether computational language models are processing language in a human-like manner. We test the ability…

Image-based environment perception is an important component especially for driver assistance systems or autonomous driving. In this scope, modern neuronal networks are used to identify multiple objects as well as the according position and…

Large Language Models (LLMs) are commonly used in Question Answering (QA) settings, increasingly in the natural sciences if not science at large. Reliable Uncertainty Quantification (UQ) is critical for the trustworthy uptake of generated…

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…

Advances in unsupervised probes such as Contrast-Consistent Search (CCS), which reveal latent beliefs without relying on token outputs, raise the question of whether these methods can reliably assess model alignment. We investigate this by…

Large Language Models (LLMs) increasingly show reasoning rationales alongside their answers, turning "reasoning" into a user-interface element. While step-by-step rationales are typically associated with model performance, how they…

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…

Confidence calibration -- the problem of predicting probability estimates representative of the true correctness likelihood -- is important for classification models in many applications. We discover that modern neural networks, unlike…

Modern neural networks have found to be miscalibrated in terms of confidence calibration, i.e., their predicted confidence scores do not reflect the observed accuracy or precision. Recent work has introduced methods for post-hoc confidence…

Trustworthy machine learning is driving a large number of ML community works in order to improve ML acceptance and adoption. The main aspect of trustworthy machine learning are the followings: fairness, uncertainty, robustness,…

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…

Scientific knowledge is constantly subject to a variety of changes due to new discoveries, alternative interpretations, and fresh perspectives. Understanding uncertainties associated with various stages of scientific inquiries is an…

There is a growing literature on reasoning by large language models (LLMs), but the discussion on the uncertainty in their responses is still lacking. Our aim is to assess the extent of confidence that LLMs have in their answers and how it…

While large language models (LLMs) improve performance by explicit reasoning, their responses are often overconfident, even though they include linguistic expressions demonstrating uncertainty. In this work, we identify what linguistic…

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,…

Counterfactual explanations are a widely used approach in Explainable AI, offering actionable insights into decision-making by illustrating how small changes to input data can lead to different outcomes. Despite their importance, evaluating…

Large language models (LLMs) have demonstrated remarkable performance, yet their diverse strengths and weaknesses prevent any single LLM from achieving dominance across all tasks. Ensembling multiple LLMs is a promising approach to generate…

In the field of Explainable AI, multiples evaluation metrics have been proposed in order to assess the quality of explanation methods w.r.t. a set of desired properties. In this work, we study the articulation between the stability,…

Uncertainty estimation is a significant issue for current large language models (LLMs) that are generally poorly calibrated and over-confident, especially with reinforcement learning from human feedback (RLHF). Unlike humans, whose…

Pre-trained language models (PLMs) may fail in giving reliable estimates of their predictive uncertainty. We take a close look into this problem, aiming to answer two questions: (1) Do PLMs learn to become calibrated in the training…