STRUM-LLM: Attributed and Structured Contrastive Summarization
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913289424863232 |
|---|---|
| author | Gunel, Beliz Wendt, James B. Xie, Jing Zhou, Yichao Vo, Nguyen Fisher, Zachary Tata, Sandeep |
| author_facet | Gunel, Beliz Wendt, James B. Xie, Jing Zhou, Yichao Vo, Nguyen Fisher, Zachary Tata, Sandeep |
| contents | Users often struggle with decision-making between two options (A vs B), as it usually requires time-consuming research across multiple web pages. We propose STRUM-LLM that addresses this challenge by generating attributed, structured, and helpful contrastive summaries that highlight key differences between the two options. STRUM-LLM identifies helpful contrast: the specific attributes along which the two options differ significantly and which are most likely to influence the user's decision. Our technique is domain-agnostic, and does not require any human-labeled data or fixed attribute list as supervision. STRUM-LLM attributes all extractions back to the input sources along with textual evidence, and it does not have a limit on the length of input sources that it can process. STRUM-LLM Distilled has 100x more throughput than the models with comparable performance while being 10x smaller. In this paper, we provide extensive evaluations for our method and lay out future directions for our currently deployed system. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_19710 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | STRUM-LLM: Attributed and Structured Contrastive Summarization Gunel, Beliz Wendt, James B. Xie, Jing Zhou, Yichao Vo, Nguyen Fisher, Zachary Tata, Sandeep Computation and Language Artificial Intelligence Information Retrieval Machine Learning Users often struggle with decision-making between two options (A vs B), as it usually requires time-consuming research across multiple web pages. We propose STRUM-LLM that addresses this challenge by generating attributed, structured, and helpful contrastive summaries that highlight key differences between the two options. STRUM-LLM identifies helpful contrast: the specific attributes along which the two options differ significantly and which are most likely to influence the user's decision. Our technique is domain-agnostic, and does not require any human-labeled data or fixed attribute list as supervision. STRUM-LLM attributes all extractions back to the input sources along with textual evidence, and it does not have a limit on the length of input sources that it can process. STRUM-LLM Distilled has 100x more throughput than the models with comparable performance while being 10x smaller. In this paper, we provide extensive evaluations for our method and lay out future directions for our currently deployed system. |
| title | STRUM-LLM: Attributed and Structured Contrastive Summarization |
| topic | Computation and Language Artificial Intelligence Information Retrieval Machine Learning |
| url | https://arxiv.org/abs/2403.19710 |