Addressing Uncertainty in LLMs to Enhance Reliability in Generative AI

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Kaur, Ramneet, Samplawski, Colin, Cobb, Adam D., Roy, Anirban, Matejek, Brian, Acharya, Manoj, Elenius, Daniel, Berenbeim, Alexander M., Pavlik, John A., Bastian, Nathaniel D., Jha, Susmit
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866929575214186496
author Kaur, Ramneet
Samplawski, Colin
Cobb, Adam D.
Roy, Anirban
Matejek, Brian
Acharya, Manoj
Elenius, Daniel
Berenbeim, Alexander M.
Pavlik, John A.
Bastian, Nathaniel D.
Jha, Susmit
author_facet Kaur, Ramneet
Samplawski, Colin
Cobb, Adam D.
Roy, Anirban
Matejek, Brian
Acharya, Manoj
Elenius, Daniel
Berenbeim, Alexander M.
Pavlik, John A.
Bastian, Nathaniel D.
Jha, Susmit
contents In this paper, we present a dynamic semantic clustering approach inspired by the Chinese Restaurant Process, aimed at addressing uncertainty in the inference of Large Language Models (LLMs). We quantify uncertainty of an LLM on a given query by calculating entropy of the generated semantic clusters. Further, we propose leveraging the (negative) likelihood of these clusters as the (non)conformity score within Conformal Prediction framework, allowing the model to predict a set of responses instead of a single output, thereby accounting for uncertainty in its predictions. We demonstrate the effectiveness of our uncertainty quantification (UQ) technique on two well known question answering benchmarks, COQA and TriviaQA, utilizing two LLMs, Llama2 and Mistral. Our approach achieves SOTA performance in UQ, as assessed by metrics such as AUROC, AUARC, and AURAC. The proposed conformal predictor is also shown to produce smaller prediction sets while maintaining the same probabilistic guarantee of including the correct response, in comparison to existing SOTA conformal prediction baseline.
format Preprint
id arxiv_https___arxiv_org_abs_2411_02381
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Addressing Uncertainty in LLMs to Enhance Reliability in Generative AI
Kaur, Ramneet
Samplawski, Colin
Cobb, Adam D.
Roy, Anirban
Matejek, Brian
Acharya, Manoj
Elenius, Daniel
Berenbeim, Alexander M.
Pavlik, John A.
Bastian, Nathaniel D.
Jha, Susmit
Artificial Intelligence
In this paper, we present a dynamic semantic clustering approach inspired by the Chinese Restaurant Process, aimed at addressing uncertainty in the inference of Large Language Models (LLMs). We quantify uncertainty of an LLM on a given query by calculating entropy of the generated semantic clusters. Further, we propose leveraging the (negative) likelihood of these clusters as the (non)conformity score within Conformal Prediction framework, allowing the model to predict a set of responses instead of a single output, thereby accounting for uncertainty in its predictions. We demonstrate the effectiveness of our uncertainty quantification (UQ) technique on two well known question answering benchmarks, COQA and TriviaQA, utilizing two LLMs, Llama2 and Mistral. Our approach achieves SOTA performance in UQ, as assessed by metrics such as AUROC, AUARC, and AURAC. The proposed conformal predictor is also shown to produce smaller prediction sets while maintaining the same probabilistic guarantee of including the correct response, in comparison to existing SOTA conformal prediction baseline.
title Addressing Uncertainty in LLMs to Enhance Reliability in Generative AI
topic Artificial Intelligence
url https://arxiv.org/abs/2411.02381