Benchmarking and Confidence Evaluation of LALMs For Temporal Reasoning

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Bhattacharya, Debarpan, Kulkarni, Apoorva, Ganapathy, Sriram
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910953447096320
author Bhattacharya, Debarpan
Kulkarni, Apoorva
Ganapathy, Sriram
author_facet Bhattacharya, Debarpan
Kulkarni, Apoorva
Ganapathy, Sriram
contents The popular success of text-based large language models (LLM) has streamlined the attention of the multimodal community to combine other modalities like vision and audio along with text to achieve similar multimodal capabilities. In this quest, large audio language models (LALMs) have to be evaluated on reasoning related tasks which are different from traditional classification or generation tasks. Towards this goal, we propose a novel dataset called temporal reasoning evaluation of audio (TREA). We benchmark open-source LALMs and observe that they are consistently behind human capabilities on the tasks in the TREA dataset. While evaluating LALMs, we also propose an uncertainty metric, which computes the invariance of the model to semantically identical perturbations of the input. Our analysis shows that the accuracy and uncertainty metrics are not necessarily correlated and thus, points to a need for wholesome evaluation of LALMs for high-stakes applications.
format Preprint
id arxiv_https___arxiv_org_abs_2505_13115
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Benchmarking and Confidence Evaluation of LALMs For Temporal Reasoning
Bhattacharya, Debarpan
Kulkarni, Apoorva
Ganapathy, Sriram
Computation and Language
Artificial Intelligence
Machine Learning
Sound
Audio and Speech Processing
The popular success of text-based large language models (LLM) has streamlined the attention of the multimodal community to combine other modalities like vision and audio along with text to achieve similar multimodal capabilities. In this quest, large audio language models (LALMs) have to be evaluated on reasoning related tasks which are different from traditional classification or generation tasks. Towards this goal, we propose a novel dataset called temporal reasoning evaluation of audio (TREA). We benchmark open-source LALMs and observe that they are consistently behind human capabilities on the tasks in the TREA dataset. While evaluating LALMs, we also propose an uncertainty metric, which computes the invariance of the model to semantically identical perturbations of the input. Our analysis shows that the accuracy and uncertainty metrics are not necessarily correlated and thus, points to a need for wholesome evaluation of LALMs for high-stakes applications.
title Benchmarking and Confidence Evaluation of LALMs For Temporal Reasoning
topic Computation and Language
Artificial Intelligence
Machine Learning
Sound
Audio and Speech Processing
url https://arxiv.org/abs/2505.13115