# YaleNLP @ PerAnsSumm 2025: Multi-Perspective Integration via Mixture-of-Agents for Enhanced Healthcare QA Summarization

arXiv: https://arxiv.org/abs/2504.03932 · HTML: https://mlsanity.com/paper/2504.03932/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use.
- Builds on 22 of its 29 references that are in the map.
- First posted on arXiv 4 Apr 2025.

## Placed in

- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 22 of 22)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization](https://mlsanity.com/paper/1808.08745/) (2018)
- [PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization](https://mlsanity.com/paper/1912.08777/) (2019)
- [Teaching Machines to Read and Comprehend](https://mlsanity.com/paper/1506.03340/) (2015)
- [Mixture-of-Agents Enhances Large Language Model Capabilities](https://mlsanity.com/paper/2406.04692/) (2024)
- [SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarization](https://mlsanity.com/paper/2111.09525/) (2021)
- [Generating Wikipedia by Summarizing Long Sequences](https://mlsanity.com/paper/1801.10198/) (2018)
- [AlignScore: Evaluating Factual Consistency with a Unified Alignment Function](https://mlsanity.com/paper/2305.16739/) (2023)
- [Demystifying Prompts in Language Models via Perplexity Estimation](https://mlsanity.com/paper/2212.04037/) (2022)
- [On Training Instance Selection for Few-Shot Neural Text Generation](https://mlsanity.com/paper/2107.03176/) (2021)
- [CQASUMM: Building References for Community Question Answering Summarization Corpora](https://mlsanity.com/paper/1811.04884/) (2018)
- [Neural Abstractive Summarization with Structural Attention](https://mlsanity.com/paper/2004.09739/) (2020)
- [AnswerSumm: A Manually-Curated Dataset and Pipeline for Answer Summarization](https://mlsanity.com/paper/2111.06474/) (2021)
- [QPO: Query-dependent Prompt Optimization via Multi-Loop Offline Reinforcement Learning](https://mlsanity.com/paper/2408.10504/) (2024)
- [No perspective, no perception!! Perspective-aware Healthcare Answer Summarization](https://mlsanity.com/paper/2406.08881/) (2024)
- [FsPONER: Few-shot Prompt Optimization for Named Entity Recognition in Domain-specific Scenarios](https://mlsanity.com/paper/2407.08035/) (2024)
- [Adaptive Few-shot Prompting for Machine Translation with Pre-trained Language Models](https://mlsanity.com/paper/2501.01679/) (2025)
- [Aspect-oriented Consumer Health Answer Summarization](https://mlsanity.com/paper/2405.06295/) (2024)

## Built on by (most cited first, 2 of 2)

- [Attention-MoA: Enhancing Mixture-of-Agents via Inter-Agent Semantic Attention and Deep Residual Synthesis](https://mlsanity.com/paper/2601.16596/) (2026)
- [Multi-LLM Collaboration for Medication Recommendation](https://mlsanity.com/paper/2512.05066/) (2025)

## Abstract (arXiv)

Automated summarization of healthcare community question-answering forums is challenging due to diverse perspectives presented across multiple user responses to each question. The PerAnsSumm Shared Task was therefore proposed to tackle this challenge by identifying perspectives from different answers and then generating a comprehensive answer to the question. In this study, we address the PerAnsSumm Shared Task using two complementary paradigms: (i) a training-based approach through QLoRA fine-tuning of LLaMA-3.3-70B-Instruct, and (ii) agentic approaches including zero- and few-shot prompting with frontier LLMs (LLaMA-3.3-70B-Instruct and GPT-4o) and a Mixture-of-Agents (MoA) framework that leverages a diverse set of LLMs by combining outputs from multi-layer feedback aggregation. For perspective span identification/classification, GPT-4o zero-shot achieves an overall score of 0.57, substantially outperforming the 0.40 score of the LLaMA baseline. With a 2-layer MoA configuration, we were able to improve LLaMA performance up by 28 percent to 0.51. For perspective-based summarization, GPT-4o zero-shot attains an overall score of 0.42 compared to 0.28 for the best LLaMA zero-shot, and our 2-layer MoA approach boosts LLaMA performance by 32 percent to 0.37. Furthermore, in few-shot setting, our results show that the sentence-transformer embedding-based exemplar selection provides more gain than manually selected exemplars on LLaMA models, although the few-shot prompting is not always helpful for GPT-4o. The YaleNLP team's approach ranked the overall second place in the shared task.