Saved in:
Bibliographic Details
Main Authors: Daull, Xavier, Bellot, Patrice, Bruno, Emmanuel, Martin, Vincent, Murisasco, Elisabeth
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2302.09051
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918180686921728
author Daull, Xavier
Bellot, Patrice
Bruno, Emmanuel
Martin, Vincent
Murisasco, Elisabeth
author_facet Daull, Xavier
Bellot, Patrice
Bruno, Emmanuel
Martin, Vincent
Murisasco, Elisabeth
contents This paper reviews the state-of-the-art of large language models (LLM) architectures and strategies for "complex" question-answering with a focus on hybrid architectures. LLM based chatbot services have allowed anyone to grasp the potential of LLM to solve many common problems, but soon discovered their limitations for complex questions. Addressing more specific, complex questions (e.g., "What is the best mix of power-generation methods to reduce climate change ?") often requires specialized architectures, domain knowledge, new skills, decomposition and multi-step resolution, deep reasoning, sensitive data protection, explainability, and human-in-the-loop processes. Therefore, we review: (1) necessary skills and tasks for handling complex questions and common LLM limits to overcome; (2) dataset, cost functions and evaluation metrics for measuring and improving (e.g. accuracy, explainability, fairness, robustness, groundedness, faithfulness, toxicity...); (3) family of solutions to overcome LLM limitations by (a) training and reinforcement (b) hybridization, (c) prompting, (d) agentic-architectures (agents, tools) and extended reasoning.
format Preprint
id arxiv_https___arxiv_org_abs_2302_09051
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Complex QA and language models hybrid architectures, Survey
Daull, Xavier
Bellot, Patrice
Bruno, Emmanuel
Martin, Vincent
Murisasco, Elisabeth
Computation and Language
Artificial Intelligence
Information Retrieval
Machine Learning
This paper reviews the state-of-the-art of large language models (LLM) architectures and strategies for "complex" question-answering with a focus on hybrid architectures. LLM based chatbot services have allowed anyone to grasp the potential of LLM to solve many common problems, but soon discovered their limitations for complex questions. Addressing more specific, complex questions (e.g., "What is the best mix of power-generation methods to reduce climate change ?") often requires specialized architectures, domain knowledge, new skills, decomposition and multi-step resolution, deep reasoning, sensitive data protection, explainability, and human-in-the-loop processes. Therefore, we review: (1) necessary skills and tasks for handling complex questions and common LLM limits to overcome; (2) dataset, cost functions and evaluation metrics for measuring and improving (e.g. accuracy, explainability, fairness, robustness, groundedness, faithfulness, toxicity...); (3) family of solutions to overcome LLM limitations by (a) training and reinforcement (b) hybridization, (c) prompting, (d) agentic-architectures (agents, tools) and extended reasoning.
title Complex QA and language models hybrid architectures, Survey
topic Computation and Language
Artificial Intelligence
Information Retrieval
Machine Learning
url https://arxiv.org/abs/2302.09051