Benchmarking Uncertainty Quantification Methods for Large Language Models with LM-Polygraph
- URL: http://arxiv.org/abs/2406.15627v1
- Date: Fri, 21 Jun 2024 20:06:31 GMT
- Title: Benchmarking Uncertainty Quantification Methods for Large Language Models with LM-Polygraph
- Authors: Roman Vashurin, Ekaterina Fadeeva, Artem Vazhentsev, Akim Tsvigun, Daniil Vasilev, Rui Xing, Abdelrahman Boda Sadallah, Lyudmila Rvanova, Sergey Petrakov, Alexander Panchenko, Timothy Baldwin, Preslav Nakov, Maxim Panov, Artem Shelmanov,
- Abstract summary: Uncertainty quantification (UQ) is becoming increasingly recognized as a critical component of applications that rely on machine learning (ML)
As with other ML models, large language models (LLMs) are prone to make incorrect predictions, hallucinate'' by fabricating claims, or simply generate low-quality output for a given input.
We introduce a novel benchmark that implements a collection of state-of-the-art UQ baselines, and provides an environment for controllable and consistent evaluation of novel techniques.
- Score: 85.51252685938564
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Uncertainty quantification (UQ) is becoming increasingly recognized as a critical component of applications that rely on machine learning (ML). The rapid proliferation of large language models (LLMs) has stimulated researchers to seek efficient and effective approaches to UQ in text generation tasks, as in addition to their emerging capabilities, these models have introduced new challenges for building safe applications. As with other ML models, LLMs are prone to make incorrect predictions, ``hallucinate'' by fabricating claims, or simply generate low-quality output for a given input. UQ is a key element in dealing with these challenges. However research to date on UQ methods for LLMs has been fragmented, with disparate evaluation methods. In this work, we tackle this issue by introducing a novel benchmark that implements a collection of state-of-the-art UQ baselines, and provides an environment for controllable and consistent evaluation of novel techniques by researchers in various text generation tasks. Our benchmark also supports the assessment of confidence normalization methods in terms of their ability to provide interpretable scores. Using our benchmark, we conduct a large-scale empirical investigation of UQ and normalization techniques across nine tasks and shed light on the most promising approaches.
Related papers
- Evaluating Generative Language Models in Information Extraction as Subjective Question Correction [49.729908337372436]
We propose a new evaluation method, SQC-Score.
Inspired by the principles in subjective question correction, we propose a new evaluation method, SQC-Score.
Results on three information extraction tasks show that SQC-Score is more preferred by human annotators than the baseline metrics.
arXiv Detail & Related papers (2024-04-04T15:36:53Z) - LUQ: Long-text Uncertainty Quantification for LLMs [29.987010627250527]
Large Language Models (LLMs) are prone to generate nonfactual content.
Uncertainty Quantification (UQ) is pivotal in enhancing our understanding of a model's confidence on its generation.
We propose textscLuq-Ensemble, a method that ensembles responses from multiple models and selects the response with the lowest uncertainty.
arXiv Detail & Related papers (2024-03-29T16:49:24Z) - RITFIS: Robust input testing framework for LLMs-based intelligent
software [6.439196068684973]
RITFIS is the first framework designed to assess the robustness of intelligent software against natural language inputs.
RITFIS adapts 17 automated testing methods, originally designed for Deep Neural Network (DNN)-based intelligent software.
It demonstrates the effectiveness of RITFIS in evaluating LLM-based intelligent software through empirical validation.
arXiv Detail & Related papers (2024-02-21T04:00:54Z) - LM-Polygraph: Uncertainty Estimation for Language Models [71.21409522341482]
Uncertainty estimation (UE) methods are one path to safer, more responsible, and more effective use of large language models (LLMs)
We introduce LM-Polygraph, a framework with implementations of a battery of state-of-the-art UE methods for LLMs in text generation tasks, with unified program interfaces in Python.
It introduces an extendable benchmark for consistent evaluation of UE techniques by researchers, and a demo web application that enriches the standard chat dialog with confidence scores.
arXiv Detail & Related papers (2023-11-13T15:08:59Z) - Are Large Language Models Really Robust to Word-Level Perturbations? [68.60618778027694]
We propose a novel rational evaluation approach that leverages pre-trained reward models as diagnostic tools.
Longer conversations manifest the comprehensive grasp of language models in terms of their proficiency in understanding questions.
Our results demonstrate that LLMs frequently exhibit vulnerability to word-level perturbations that are commonplace in daily language usage.
arXiv Detail & Related papers (2023-09-20T09:23:46Z) - Uncertainty Quantification in Machine Learning for Engineering Design
and Health Prognostics: A Tutorial [12.570694576213244]
Uncertainty quantification (UQ) functions as an essential layer of safety assurance that could lead to more principled decision making.
This tutorial provides a holistic lens on emerging UQ methods for ML models with a particular focus on neural networks.
We discuss the increasingly important role of UQ of ML models in solving challenging problems in engineering design and health prognostics.
arXiv Detail & Related papers (2023-05-07T03:12:03Z) - The Integration of Machine Learning into Automated Test Generation: A
Systematic Mapping Study [15.016047591601094]
We characterize emerging research, examining testing practices, researcher goals, ML techniques applied, evaluation, and challenges.
ML generates input for system, GUI, unit, performance, and testing or improves the performance of existing generation methods.
arXiv Detail & Related papers (2022-06-21T09:26:25Z) - Text Generation with Efficient (Soft) Q-Learning [91.47743595382758]
Reinforcement learning (RL) offers a more flexible solution by allowing users to plug in arbitrary task metrics as reward.
We introduce a new RL formulation for text generation from the soft Q-learning perspective.
We apply the approach to a wide range of tasks, including learning from noisy/negative examples, adversarial attacks, and prompt generation.
arXiv Detail & Related papers (2021-06-14T18:48:40Z) - A Review of Uncertainty Quantification in Deep Learning: Techniques,
Applications and Challenges [76.20963684020145]
Uncertainty quantification (UQ) plays a pivotal role in reduction of uncertainties during both optimization and decision making processes.
Bizarre approximation and ensemble learning techniques are two most widely-used UQ methods in the literature.
This study reviews recent advances in UQ methods used in deep learning and investigates the application of these methods in reinforcement learning.
arXiv Detail & Related papers (2020-11-12T06:41:05Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.