# Empirical Analysis of Dialogue Relation Extraction with Large Language Models

arXiv: https://arxiv.org/abs/2404.17802 · HTML: https://mlsanity.com/paper/2404.17802/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 39 references that are in the map.
- First posted on arXiv 27 Apr 2024.

## Builds on (most cited first, 30 of 30)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [BLOOM: A 176B-Parameter Open-Access Multilingual Language Model](https://mlsanity.com/paper/2211.05100/) (2022)
- [Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour](https://mlsanity.com/paper/1706.02677/) (2017)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations](https://mlsanity.com/paper/1810.02508/) (2018)
- [DocRED: A Large-Scale Document-Level Relation Extraction Dataset](https://mlsanity.com/paper/1906.06127/) (2019)
- [Structured Prediction as Translation between Augmented Natural Languages](https://mlsanity.com/paper/2101.05779/) (2021)
- [Ask Me Anything: A simple strategy for prompting language models](https://mlsanity.com/paper/2210.02441/) (2022)
- [Large Language Model Is Not a Good Few-shot Information Extractor, but a Good Reranker for Hard Samples!](https://mlsanity.com/paper/2303.08559/) (2023)
- [Emotion Detection on TV Show Transcripts with Sequence-based Convolutional Neural Networks](https://mlsanity.com/paper/1708.04299/) (2017)
- [Revisiting Relation Extraction in the era of Large Language Models](https://mlsanity.com/paper/2305.05003/) (2023)
- [Dialogue-Based Relation Extraction](https://mlsanity.com/paper/2004.08056/) (2020)
- [GPT-RE: In-context Learning for Relation Extraction using Large Language Models](https://mlsanity.com/paper/2305.02105/) (2023)
- [Aligning Instruction Tasks Unlocks Large Language Models as Zero-Shot Relation Extractors](https://mlsanity.com/paper/2305.11159/) (2023)
- [GDPNet: Refining Latent Multi-View Graph for Relation Extraction](https://mlsanity.com/paper/2012.06780/) (2020)
- [Revisiting Large Language Models as Zero-shot Relation Extractors](https://mlsanity.com/paper/2310.05028/) (2023)
- [Graph Based Network with Contextualized Representations of Turns in Dialogue](https://mlsanity.com/paper/2109.04008/) (2021)
- [A sequence-to-sequence approach for document-level relation extraction](https://mlsanity.com/paper/2204.01098/) (2022)
- [FastRE: Towards Fast Relation Extraction with Convolutional Encoder and Improved Cascade Binary Tagging Framework](https://mlsanity.com/paper/2205.02490/) (2022)
- [Unlocking Instructive In-Context Learning with Tabular Prompting for Relational Triple Extraction](https://mlsanity.com/paper/2402.13741/) (2024)
- [Hierarchical Dialogue Understanding with Special Tokens and Turn-level Attention](https://mlsanity.com/paper/2305.00262/) (2023)
- [GRASP: Guiding model with RelAtional Semantics using Prompt for Dialogue Relation Extraction](https://mlsanity.com/paper/2208.12494/) (2022)

## Built on by (most cited first, 4 of 4)

- [MLlm-DR: Towards Explainable Depression Recognition with MultiModal Large Language Models](https://mlsanity.com/paper/2507.05591/) (2025)
- [Subversive Characters and Stereotyping Readers: Characterizing Queer Relationalities with Dialogue-Based Relation Extraction](https://mlsanity.com/paper/2410.14978/) (2024)
- [Dialogue-Based Multi-Dimensional Relationship Extraction from Novels](https://mlsanity.com/paper/2507.04852/) (2025)
- [From "Strings" to "Things" for Personal Knowledge Graphs: Evaluating LLM Triple Extraction for Recommendation Systems](https://mlsanity.com/paper/2607.00003/) (2026)

## Abstract (arXiv)

Dialogue relation extraction (DRE) aims to extract relations between two arguments within a dialogue, which is more challenging than standard RE due to the higher person pronoun frequency and lower information density in dialogues. However, existing DRE methods still suffer from two serious issues: (1) hard to capture long and sparse multi-turn information, and (2) struggle to extract golden relations based on partial dialogues, which motivates us to discover more effective methods that can alleviate the above issues. We notice that the rise of large language models (LLMs) has sparked considerable interest in evaluating their performance across diverse tasks. To this end, we initially investigate the capabilities of different LLMs in DRE, considering both proprietary models and open-source models. Interestingly, we discover that LLMs significantly alleviate two issues in existing DRE methods. Generally, we have following findings: (1) scaling up model size substantially boosts the overall DRE performance and achieves exceptional results, tackling the difficulty of capturing long and sparse multi-turn information; (2) LLMs encounter with much smaller performance drop from entire dialogue setting to partial dialogue setting compared to existing methods; (3) LLMs deliver competitive or superior performances under both full-shot and few-shot settings compared to current state-of-the-art; (4) LLMs show modest performances on inverse relations but much stronger improvements on general relations, and they can handle dialogues of various lengths especially for longer sequences.