# UMB@PerAnsSumm 2025: Enhancing Perspective-Aware Summarization with Prompt Optimization and Supervised Fine-Tuning

Source: [UMB@PerAnsSumm 2025: Enhancing Perspective-Aware Summarization with Prompt Optimization and Supervised Fine-Tuning](<https://www.sota2.com/research/paper/68fa77791e209131cea73650>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-11-27T05:01:19.526Z

Authors: Kristin Qi, Youxiang Zhu, Xiaohui Liang

Published: 2025-03-14T06:29:51.000Z

## Abstract

We present our approach to the PerAnsSumm Shared Task, which involves perspective span identification and perspective-aware summarization in community question-answering (CQA) threads. For span identification, we adopt ensemble learning that integrates three transformer models through averaging to exploit individual model strengths, achieving an 82.91% F1-score on test data. For summarization, we design a suite of Chain-of-Thought (CoT) prompting strategies that incorporate keyphrases and guide information to structure summary generation into manageable steps. To further enhance summary quality, we apply prompt optimization using the DSPy framework and supervised fine-tuning (SFT) on Llama-3 to adapt the model to domain-specific data. Experimental results on validation and test sets show that structured prompts with keyphrases and guidance improve summaries aligned with references, while the combination of prompt optimization and fine-tuning together yields significant improvement in both relevance and factuality evaluation metrics.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2503.11118>)

[PDF](<https://arxiv.org/pdf/2503.11118.pdf>)
