LLM Augmentations to support Analytical Reasoning over Multiple Documents

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yousuf, Raquib Bin, Defelice, Nicholas, Sharma, Mandar, Xu, Shengzhe, Ramakrishnan, Naren
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929603819339776
author Yousuf, Raquib Bin
Defelice, Nicholas
Sharma, Mandar
Xu, Shengzhe
Ramakrishnan, Naren
author_facet Yousuf, Raquib Bin
Defelice, Nicholas
Sharma, Mandar
Xu, Shengzhe
Ramakrishnan, Naren
contents Building on their demonstrated ability to perform a variety of tasks, we investigate the application of large language models (LLMs) to enhance in-depth analytical reasoning within the context of intelligence analysis. Intelligence analysts typically work with massive dossiers to draw connections between seemingly unrelated entities, and uncover adversaries' plans and motives. We explore if and how LLMs can be helpful to analysts for this task and develop an architecture to augment the capabilities of an LLM with a memory module called dynamic evidence trees (DETs) to develop and track multiple investigation threads. Through extensive experiments on multiple datasets, we highlight how LLMs, as-is, are still inadequate to support intelligence analysts and offer recommendations to improve LLMs for such intricate reasoning applications.
format Preprint
id arxiv_https___arxiv_org_abs_2411_16116
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle LLM Augmentations to support Analytical Reasoning over Multiple Documents
Yousuf, Raquib Bin
Defelice, Nicholas
Sharma, Mandar
Xu, Shengzhe
Ramakrishnan, Naren
Computation and Language
Artificial Intelligence
Building on their demonstrated ability to perform a variety of tasks, we investigate the application of large language models (LLMs) to enhance in-depth analytical reasoning within the context of intelligence analysis. Intelligence analysts typically work with massive dossiers to draw connections between seemingly unrelated entities, and uncover adversaries' plans and motives. We explore if and how LLMs can be helpful to analysts for this task and develop an architecture to augment the capabilities of an LLM with a memory module called dynamic evidence trees (DETs) to develop and track multiple investigation threads. Through extensive experiments on multiple datasets, we highlight how LLMs, as-is, are still inadequate to support intelligence analysts and offer recommendations to improve LLMs for such intricate reasoning applications.
title LLM Augmentations to support Analytical Reasoning over Multiple Documents
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2411.16116