# Enhancing Answer Selection in Community Question Answering with Pre-trained and Large Language Models

arXiv: https://arxiv.org/abs/2311.17502 · HTML: https://mlsanity.com/paper/2311.17502/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 38 references that are in the map.
- First posted on arXiv 29 Nov 2023.

## Builds on (most cited first, 19 of 19)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [Towards Expert-Level Medical Question Answering with Large Language Models](https://mlsanity.com/paper/2305.09617/) (2023)
- [A Structured Self-attentive Sentence Embedding](https://mlsanity.com/paper/1703.03130/) (2017)
- [Generate rather than Retrieve: Large Language Models are Strong Context Generators](https://mlsanity.com/paper/2209.10063/) (2022)
- [Enhanced LSTM for Natural Language Inference](https://mlsanity.com/paper/1609.06038/) (2016)
- [Can large language models reason about medical questions?](https://mlsanity.com/paper/2207.08143/) (2022)
- [Natural Language Inference by Tree-Based Convolution and Heuristic Matching](https://mlsanity.com/paper/1512.08422/) (2015)
- [Multi-domain Dialogue State Tracking as Dynamic Knowledge Graph Enhanced Question Answering](https://mlsanity.com/paper/1911.06192/) (2019)
- [Prophet: Prompting Large Language Models with Complementary Answer Heuristics for Knowledge-based Visual Question Answering](https://mlsanity.com/paper/2303.01903/) (2023)
- [Benchmarking Knowledge-Enhanced Commonsense Question Answering via Knowledge-to-Text Transformation](https://mlsanity.com/paper/2101.00760/) (2021)
- [MaScQA: A Question Answering Dataset for Investigating Materials Science Knowledge of Large Language Models](https://mlsanity.com/paper/2308.09115/) (2023)
- [Towards Reliable and Fluent Large Language Models: Incorporating Feedback Learning Loops in QA Systems](https://mlsanity.com/paper/2309.06384/) (2023)
- [Graph-Based Tri-Attention Network for Answer Ranking in CQA](https://mlsanity.com/paper/2103.03583/) (2021)
- [Global Thread-Level Inference for Comment Classification in Community Question Answering](https://mlsanity.com/paper/1911.08755/) (2019)
- [Large Language Models Need Holistically Thought in Medical Conversational QA](https://mlsanity.com/paper/2305.05410/) (2023)
- [KEPR: Knowledge Enhancement and Plausibility Ranking for Generative Commonsense Question Answering](https://mlsanity.com/paper/2305.08347/) (2023)
- [Promotion of Answer Value Measurement with Domain Effects in Community Question Answering Systems](https://mlsanity.com/paper/1906.00156/) (2019)
- [Knowledge-Enhanced Attentive Learning for Answer Selection in Community Question Answering Systems](https://mlsanity.com/paper/1912.07915/) (2019)

## Built on by (most cited first, 3 of 3)

- [Automatic Database Configuration Debugging using Retrieval-Augmented Language Models](https://mlsanity.com/paper/2412.07548/) (2024)
- [ComRAG: Retrieval-Augmented Generation with Dynamic Vector Stores for Real-time Community Question Answering in Industry](https://mlsanity.com/paper/2506.21098/) (2025)
- [Multi-granular Training Strategies for Robust Multi-hop Reasoning Over Noisy and Heterogeneous Knowledge Sources](https://mlsanity.com/paper/2502.05944/) (2025)

## Abstract (arXiv)

Community Question Answering (CQA) becomes increasingly prevalent in recent years. However, there are a large number of answers, which is difficult for users to select the relevant answers. Therefore, answer selection is a very significant subtask of CQA. In this paper, we first propose the Question-Answer cross attention networks (QAN) with pre-trained models for answer selection and utilize large language model (LLM) to perform answer selection with knowledge augmentation. Specifically, we apply the BERT model as the encoder layer to do pre-training for question subjects, question bodies and answers, respectively, then the cross attention mechanism selects the most relevant answer for different questions. Experiments show that the QAN model achieves state-of-the-art performance on two datasets, SemEval2015 and SemEval2017. Moreover, we use the LLM to generate external knowledge from questions and correct answers to achieve knowledge augmentation for the answer selection task by LLM, while optimizing the prompt of LLM in different aspects. The results show that the introduction of external knowledge can improve the correct answer selection rate of LLM on datasets SemEval2015 and SemEval2017. Meanwhile, LLM can also select the correct answer on more questions by optimized prompt.