Challenge: Conventional evaluation methods often overlook variances in model behavior across different levels of structural complexity on interaction graphs.
Approach: They propose a methodological pipeline to investigate model performance across structural attributes of conversations.
Outcome: The proposed method analyzes the performance of an LLM to classify multi-party conversations . it shows that response selection relies more on the textual content of conversations compared to addressee recognition .

Similar Papers

Is ChatGPT a Good Multi-Party Conversation Solver? (2023.findings-emnlp)

Copied to clipboard

Challenge: Large Language Models (LLMs) are powerful tools for multi-party conversations, but their capacity to handle multi-parties remains unexplored.
Approach: They propose to evaluate ChatGPT and GPT-4's zero-shot learning capabilities within the context of multi-party conversations (MPCs) they also propose to incorporate MPC structures, encompassing both speaker and addressee architecture.
Outcome: The proposed models perform poorly on a number of MPC tasks while GPT-4 performs well on speaker and addressee architecture.
MPC-BERT: A Pre-Trained Language Model for Multi-Party Conversation Understanding (2021.acl-long)

Copied to clipboard

Challenge: Existing models for multi-party conversation represent interlocutors and utterances individually . existing methods ignore complicated structure of MPC which may provide crucial interlocutor and tertiary semantics.
Approach: They propose a pre-trained model for multi-party conversation that considers learning who says what to whom in a unified model with elaborated self-supervised tasks.
Outcome: The proposed model outperforms existing models on three downstream tasks at two benchmarks.
Simple Agents, Biased Judges: Efficient Multi-Party Dialogue Generation & The Evaluation Gap (2026.acl-long)

Copied to clipboard

Challenge: Multiparty social dialogue is difficult to formalize and expensive to evaluate, especially at scale.
Approach: They propose a lightweight and controllable multi-party dialoguegeneration framework as an experimental instrument for studying generation and evaluation in social interaction.
Outcome: The proposed framework shows that human judgments against state-of-the-art LLM judges are consistent with human preferences for naturalness, engagingness, and overall quality in multi-party social dialogue.
Do LLMs Understand Dialogues? A Case Study on Dialogue Acts (2025.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) have shown remarkable performance on many unseen tasks in a zero-shot setting.
Approach: They propose to identify three key pre-tasks essential for accurate DA prediction: Turn Management, Communicative Function Identification, and Dialogue Structure Prediction.
Outcome: The proposed model fails to outperform basic rule-based tasks on three key pre-tasks, and the results suggest that the model is flawed.
Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey (2024.naacl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) are now commonplace in conversation applications, but their misuse for generating harmful responses has raised serious societal concerns.
Approach: They provide a comprehensive overview of recent studies covering attacks, defenses, and evaluations of Large Language Models (LLMs) .
Outcome: The proposed review summarizes three aspects of LLM conversation safety: attacks, defenses, and evaluations.
Response Selection for Multi-Party Conversations with Dynamic Topic Tracking (2020.emnlp-main)

Copied to clipboard

Challenge: Existing response selection methods focus on a two-party single-conversation scenario.
Approach: They propose a multi-task learning framework that frames response selection as a dynamic topic tracking task to match the topic between the response and relevant conversation context.
Outcome: The proposed framework outperforms existing methods on an Ubuntu IRC dataset in response selection and topic disentanglement tasks.
In Search of the Lost Arch in Dialogue: A Dependency Dialogue Acts Corpus for Multi-Party Dialogues (2025.findings-acl)

Copied to clipboard

Challenge: Understanding speaker intentions remains a challenge in NLP . a number of corpora annotated using theoretical frameworks of dialogue focus on utterance-level labeling of speaker intent, missing wider context, or the rhetorical structure of a dialogue.
Approach: They propose to annotate a corpus of 33 dialogues and over 9,000 utterance units using the Dependency Dialogue Acts framework.
Outcome: The proposed corpus spans four genres of multi-party conversations from different modalities.
Are Large Language Models (LLMs) Good Social Predictors? (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing studies suggest that Large Language Models can generate human-like responses, but it is unclear how well they work and where the plausible predictions derive from.
Approach: They propose to use LLMs to generate human-like responses by mutability and accessibility of social inputs to perform a social prediction task.
Outcome: The proposed model performs well in three realistic settings and a novel social prediction task.
Addressee and Response Selection for Multilingual Conversation (C18-1)

Copied to clipboard

Challenge: Developing conversational systems that can converse in many languages is an interesting challenge for natural language processing.
Approach: They propose multilingual addressee and response selection task for conversational systems . they use a multilingual conversation dataset to evaluate their methods .
Outcome: The proposed methods can predict addressee and response in multiple languages . they show that the methods work in a multilingual conversation dataset .
From Tools to Teammates: Evaluating LLMs in Multi-Session Coding Interactions (2025.acl-long)

Copied to clipboard

Challenge: Large Language Models excel at solving individual problems in isolation, but are they able to effectively collaborate over long-term interactions?
Approach: They propose to use a multi-session dataset to test LLMs' ability to track and execute simple coding instructions amid irrelevant information, simulating a realistic setting.
Outcome: The proposed model performs poorly when instructions are spread across sessions, suggesting that they are not able to integrate information over long interactions.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations