paper-with-me

홈 › Papers

Do LLMs suffer from Multi-Party Hangover? A Diagnostic Approach to Addressee Recognition and Response Selection in Conversations

2024-09-27 · Nicolò Penzo, Maryam Sajedinia, Bruno Lepri, Sara Tonelli, Marco Guerini

Assessing the performance of systems to classify Multi-Party Conversations (MPC) is challenging due to the interconnection between linguistic and structural characteristics of conversations. Conventional evaluation methods often overlook variances in model behavior across different levels of structural complexity on interaction graphs. In this work, we propose a methodological pipeline to investigate model performance across specific structural attributes of conversations. As a proof of concept we focus on Response Selection and Addressee Recognition tasks, to diagnose model weaknesses. To this end, we extract representative diagnostic subdatasets with a fixed number of users and a good structural variety from a large and open corpus of online MPCs. We further frame our work in terms of data minimization, avoiding the use of original usernames to preserve privacy, and propose alternatives to using original text messages. Results show that response selection relies more on the textual content of conversations, while addressee recognition requires capturing their structural dimension. Using an LLM in a zero-shot setting, we further highlight how sensitivity to prompt variations is task-dependent.

📄 PDF Abstract BibTeX arXiv:2409.18602

Code (1)

dhfbk/MPH 공식 구현

Tasks

Diagnostic

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Causal Hangover Effects

2024-12-30 · Andreas Santucci, Eric Lax

It's not unreasonable to think that in-game sporting performance can be affected partly by what takes place off the court. We can't observe what happens between games directly. Instead, we proxy for the possibility of at…

DeliChess: A Multi-party Dialogue Dataset for Deliberation in Chess Puzzle Solving

2026-06-03 · Xiaochen Zhu, Georgi Karadzhov, Tom Stafford, Andreas Vlachos arxiv

Multi-party dialogue is a critical setting for studying collaborative reasoning and decision-making, yet existing datasets rarely focus on structured, reasoning-intensive tasks. We introduce DeliChess, a dataset of group…

Multi-Party Supervised Fine-tuning of Language Models for Multi-Party Dialogue Generation

2024-12-06 · Xiaoyu Wang, Ningyuan Xi, Teng Chen, Qingqing Gu 외

Large Language Models (LLM) are usually fine-tuned to participate in dyadic or two-party dialogues, which can not adapt well to multi-party dialogues (MPD), which hinders their applications in such scenarios including mu…

Dialogue Generation

Diagnosing Korean-Language LLM Political Bias via Census-Grounded Agent Simulation

2026-05-18 · Sungwoo Kang arxiv

Large language models (LLMs) exhibit systematic political biases in voter simulations, but their underlying mechanisms and cross-lingual generalizations remain poorly understood. We introduce Dynamo-K, a census-grounded …

Can MLLMs Generalize to Multi-Party dialog? Exploring Multilingual Response Generation in Complex Scenarios

2025-01-20 · Zhongtian Hu, Yiwen Cui, Ronghan Li, Meng Zhao 외

Current multilingual large language models(MLLMs) still focus on simple question-answering formats, often overlooking more complex dialogue scenarios. In other words, their capabilities of multilingual large models have …

Question AnsweringResponse Generation