Extracting Self-Consistent Causal Insights from Users Feedback with LLMs and In-context Learning ...
Microsoft Windows Feedback Hub is designed to receive customer feedback on a wide variety of subjects including critical topics such as power and battery. Feedback is one of the most effective ways to have a grasp of users' experience with Windows and its ecosystem. However, the sheer volume of...
Main Authors: | , , , |
---|---|
Format: | Article in Journal/Newspaper |
Language: | unknown |
Published: |
arXiv
2023
|
Subjects: | |
Online Access: | https://dx.doi.org/10.48550/arxiv.2312.06820 https://arxiv.org/abs/2312.06820 |
id |
ftdatacite:10.48550/arxiv.2312.06820 |
---|---|
record_format |
openpolar |
spelling |
ftdatacite:10.48550/arxiv.2312.06820 2024-01-28T10:05:24+01:00 Extracting Self-Consistent Causal Insights from Users Feedback with LLMs and In-context Learning ... Abdali, Sara Parikh, Anjali Lim, Steve Kiciman, Emre 2023 https://dx.doi.org/10.48550/arxiv.2312.06820 https://arxiv.org/abs/2312.06820 unknown arXiv Creative Commons Attribution Non Commercial Share Alike 4.0 International https://creativecommons.org/licenses/by-nc-sa/4.0/legalcode cc-by-nc-sa-4.0 Artificial Intelligence cs.AI Computation and Language cs.CL Machine Learning cs.LG Methodology stat.ME FOS Computer and information sciences Article Preprint CreativeWork article 2023 ftdatacite https://doi.org/10.48550/arxiv.2312.06820 2024-01-04T23:54:53Z Microsoft Windows Feedback Hub is designed to receive customer feedback on a wide variety of subjects including critical topics such as power and battery. Feedback is one of the most effective ways to have a grasp of users' experience with Windows and its ecosystem. However, the sheer volume of feedback received by Feedback Hub makes it immensely challenging to diagnose the actual cause of reported issues. To better understand and triage issues, we leverage Double Machine Learning (DML) to associate users' feedback with telemetry signals. One of the main challenges we face in the DML pipeline is the necessity of domain knowledge for model design (e.g., causal graph), which sometimes is either not available or hard to obtain. In this work, we take advantage of reasoning capabilities in Large Language Models (LLMs) to generate a prior model that which to some extent compensates for the lack of domain knowledge and could be used as a heuristic for measuring feedback informativeness. Our LLM-based approach is ... Article in Journal/Newspaper DML DataCite Metadata Store (German National Library of Science and Technology) |
institution |
Open Polar |
collection |
DataCite Metadata Store (German National Library of Science and Technology) |
op_collection_id |
ftdatacite |
language |
unknown |
topic |
Artificial Intelligence cs.AI Computation and Language cs.CL Machine Learning cs.LG Methodology stat.ME FOS Computer and information sciences |
spellingShingle |
Artificial Intelligence cs.AI Computation and Language cs.CL Machine Learning cs.LG Methodology stat.ME FOS Computer and information sciences Abdali, Sara Parikh, Anjali Lim, Steve Kiciman, Emre Extracting Self-Consistent Causal Insights from Users Feedback with LLMs and In-context Learning ... |
topic_facet |
Artificial Intelligence cs.AI Computation and Language cs.CL Machine Learning cs.LG Methodology stat.ME FOS Computer and information sciences |
description |
Microsoft Windows Feedback Hub is designed to receive customer feedback on a wide variety of subjects including critical topics such as power and battery. Feedback is one of the most effective ways to have a grasp of users' experience with Windows and its ecosystem. However, the sheer volume of feedback received by Feedback Hub makes it immensely challenging to diagnose the actual cause of reported issues. To better understand and triage issues, we leverage Double Machine Learning (DML) to associate users' feedback with telemetry signals. One of the main challenges we face in the DML pipeline is the necessity of domain knowledge for model design (e.g., causal graph), which sometimes is either not available or hard to obtain. In this work, we take advantage of reasoning capabilities in Large Language Models (LLMs) to generate a prior model that which to some extent compensates for the lack of domain knowledge and could be used as a heuristic for measuring feedback informativeness. Our LLM-based approach is ... |
format |
Article in Journal/Newspaper |
author |
Abdali, Sara Parikh, Anjali Lim, Steve Kiciman, Emre |
author_facet |
Abdali, Sara Parikh, Anjali Lim, Steve Kiciman, Emre |
author_sort |
Abdali, Sara |
title |
Extracting Self-Consistent Causal Insights from Users Feedback with LLMs and In-context Learning ... |
title_short |
Extracting Self-Consistent Causal Insights from Users Feedback with LLMs and In-context Learning ... |
title_full |
Extracting Self-Consistent Causal Insights from Users Feedback with LLMs and In-context Learning ... |
title_fullStr |
Extracting Self-Consistent Causal Insights from Users Feedback with LLMs and In-context Learning ... |
title_full_unstemmed |
Extracting Self-Consistent Causal Insights from Users Feedback with LLMs and In-context Learning ... |
title_sort |
extracting self-consistent causal insights from users feedback with llms and in-context learning ... |
publisher |
arXiv |
publishDate |
2023 |
url |
https://dx.doi.org/10.48550/arxiv.2312.06820 https://arxiv.org/abs/2312.06820 |
genre |
DML |
genre_facet |
DML |
op_rights |
Creative Commons Attribution Non Commercial Share Alike 4.0 International https://creativecommons.org/licenses/by-nc-sa/4.0/legalcode cc-by-nc-sa-4.0 |
op_doi |
https://doi.org/10.48550/arxiv.2312.06820 |
_version_ |
1789331677231710208 |