Related papers: Towards Reliable Truth-Aligned Uncertainty Estimat…
Large language models (LLMs) specializing in natural language generation (NLG) have recently started exhibiting promising capabilities across a variety of domains. However, gauging the trustworthiness of responses generated by LLMs remains…
To build robust, fair, and safe AI systems, we would like our classifiers to say ``I don't know'' when facing test examples that are difficult or fall outside of the training classes.The ubiquitous strategy to predict under uncertainty is…
Machine unlearning for large language models (LLMs) aims to remove undesired data, knowledge, and behaviors (e.g., for safety, privacy, or copyright) while preserving useful model capabilities. Despite rapid progress over the past two…
This study evaluates large language models as estimable classifiers and clarifies how modeling choices shape downstream measurement error. Revisiting the Economic Policy Uncertainty index, we show that contemporary classifiers substantially…
Retrieval Augmented Generation (RAG) improves the question answering capabilities of Large Language Models (LLMs) by incorporating external knowledge and has recently been extended to multimodal settings through Vision-Language Models…
Large Language Models have significantly advanced natural language processing tasks, but remain prone to generating incorrect or misleading but plausible arguments. This issue, known as hallucination, is particularly concerning in…
Emergence of artificial intelligence techniques in biomedical applications urges the researchers to pay more attention on the uncertainty quantification (UQ) in machine-assisted medical decision making. For classification tasks, prior…
Large language models (LLMs) often make accurate next token predictions but their confidence in these predictions can be poorly calibrated: high-confidence predictions are frequently wrong, and low-confidence predictions may be correct.…
Large Language Models (LLMs) have shown remarkable performance across a wide range of downstream tasks. However, it is challenging for users to discern whether the responses of LLM are generated with certainty or are fabricated to meet user…
Comprehensive evaluation of Large Language Models (LLMs) is an open research problem. Existing evaluations rely on deterministic point estimates generated via greedy decoding. However, we find that deterministic evaluations fail to capture…
When does a large language model (LLM) know what it does not know? Uncertainty quantification (UQ) provides measures of uncertainty, such as an estimate of the confidence in an LLM's generated output, and is therefore increasingly…
Large language models (LLMs) have demonstrated strong capabilities in complex reasoning tasks, yet their decision-making processes remain difficult to interpret. Existing explanation methods often lack trustworthy structural insight and are…
In safety-critical applications, language models should be able to characterize their uncertainty with meaningful probabilities. Many uncertainty quantification approaches require supervised data; however, finding suitable unseen…
Large Language Models (LLMs) are increasingly excelling and outpacing human performance on many tasks. However, to improve LLM reasoning, researchers either rely on ad-hoc generated datasets or formal mathematical proof systems such as the…
We introduce a novel approach for calibrating uncertainty quantification (UQ) tailored for multi-modal large language models (LLMs). Existing state-of-the-art UQ methods rely on consistency among multiple responses generated by the LLM on…
Benchmarks underpin how progress in large language models (LLMs) is measured and trusted. Yet our analyses reveal that apparent convergence in benchmark accuracy can conceal deep epistemic divergence. Using two major reasoning benchmarks -…
When using large language models (LLMs) in high-stakes applications, we need to know when we can trust their predictions. Some works argue that prompting high-performance LLMs is sufficient to produce calibrated uncertainties, while others…
Automated scientific discovery using large language models relies on identifying genuinely novel solutions. Standard reinforcement learning penalizes high-variance mutations, which leads the policy to prioritize familiar patterns. As a…
A reliable uncertainty estimation method is the foundation of many modern out-of-distribution (OOD) detectors, which are critical for safe deployments of deep learning models in the open world. In this work, we propose TULiP, a…
This paper studies the problem of post-hoc calibration of machine learning classifiers. We introduce the following desiderata for uncertainty calibration: (a) accuracy-preserving, (b) data-efficient, and (c) high expressive power. We show…