DIALOGUE TASKS

A Reasoner for Real-World Event Detection: Scaling Reinforcement Learning via Adaptive Perplexity-Aware Sampling Strategy (2025.emnlp-industry)

Challenge:	Existing approaches for goal-oriented dialogue policy learning focus on the target agent policy and treat the opposite agent policy as part of the environment.
Approach:	They propose a framework for policy learning in goal-oriented dialogues that uses the opposite agent's policy estimation to improve the target agent by regarding it as part of the target policy.
Outcome:	The proposed framework shows superior performance over state-of-the-art models on cooperative and competitive dialogue tasks.

Copied to clipboard

Xiaoyun Zhang, Jingqing Ruan, Xing Ma, Yawen Zhu, Jiansong Chen, Ke Zeng, Xunliang Cai

ASTRO: Automatic Strategy Optimization For Non-Cooperative Dialogues (2025.findings-acl)

Challenge:	Existing methods for abnormal event detection face two predominant limitations . existing methods rely on specialized small models and are limited by performance bottlenecks .
Approach:	They propose a framework that leverages the advanced reasoning capabilities of large language models for abnormal event detection.
Outcome:	The proposed framework achieves the highest F1 score and an average improvement of 9.59% in OOD transfer tests.

Copied to clipboard

Yikuan Hu, Chen Huang, Wenqiang Lei

Strength Lies in Differences! Improving Strategy Planning for Non-collaborative Dialogues via Diversified User Simulation (2024.emnlp-main)

Challenge:	Existing methods for optimizing dialogues require substantial human effort for strategy optimization.
Approach:	They propose a fully automated solution that leverages large language models’ self-envolving capabilities to optimize dialogue strategies.
Outcome:	The proposed solution significantly improves on baseline models across non-cooperative dialogue tasks, highlighting the potential for autonomously developing such agents without human intervention.

Copied to clipboard

Tong Zhang, Chen Huang, Yang Deng, Hongru Liang, Jia Liu, Zujie Wen, Wenqiang Lei, Tat-Seng Chua

Seamlessly Integrating Factual Information and Social Content with Persuasive Dialogue (2022.aacl-main)

Challenge:	Non-collaborative dialogue agents are expected to engage in strategic conversations with diverse users, and this poses two main challenges for existing dialogue agents: 1) the inability to integrate user-specific characteristics into the strategic planning; 2) the difficulty of training strategic planners that can be generalized to diverse users.
Approach:	They propose to integrate a user-aware strategic planning module and a population-based training paradigm into a non-collaborative dialogue agent for securing a mutual agreement that leans favorably towards the system's objectives.
Outcome:	The proposed model can be used to achieve a mutual agreement that leans favorably towards the system's objectives.

Copied to clipboard

Maximillian Chen, Weiyan Shi, Feifan Yan, Ryan Hou, Jingwen Zhang, Saurav Sahay, Zhou Yu

InstructDial: Improving Zero and Few-shot Generalization in Dialogue through Instruction Tuning (2022.emnlp-main)

Challenge:	Persuasive dialogue systems are designed for chatbots to communicate with and influence users with specific goals.
Approach:	They propose a modular dialogue system framework that integrates factual information and social content into persuasive dialogues.
Outcome:	The proposed framework is generalizable to any dialogue tasks that have mixed social and task contents.

Copied to clipboard

Prakhar Gupta, Cathy Jiao, Yi-Ting Yeh, Shikib Mehri, Maxine Eskenazi, Jeffrey Bigham

Semantic-based Pre-training for Dialogue Understanding (2022.coling-1)

Challenge:	Instruction tuning is emerging in NLP, but has not been explored for dialogue-related tasks.
Approach:	They propose an instruction tuning framework for dialogue that leverages natural language instructions with language models to induce zero-shot generalization on unseen tasks.
Outcome:	The proposed framework enables good zero-shot performance on unseen datasets and tasks such as dialogue evaluation and intent detection.

Copied to clipboard

Xuefeng Bai, Linfeng Song, Yue Zhang

Semantic Text Processing

Challenge:	Pre-trained language models are weak in understanding the main semantic meaning of a dialogue context.
Approach:	They propose a semantic-based framework that leverages explicit semantic knowledge to capture the core semantic information in dialogues during pre-training.
Outcome:	The proposed model is superior to existing models on chit-chats and task-oriented dialogues.

A Versatile Adaptive Curriculum Learning Framework for Task-oriented Dialogue Policy Learning (2022.findings-naacl)

Copied to clipboard

Yang Zhao, Hua Qin, Wang Zhenyu, Changxi Zhu, Shihan Wang

Learning Dialogue Representations from Consecutive Utterances (2022.naacl-main)

Challenge:	Existing training paradigms for dialogue policy learning with brute-force random sampling are expensive and lack reliable evaluation of difficulty scores.
Approach:	They propose a flexible adaptive curriculum learning framework that integrates curriculum learning with a generic global curriculum.
Outcome:	The proposed framework improves learning performance and efficiency on three public dialogue datasets.

Copied to clipboard

Zhihan Zhou, Dejiao Zhang, Wei Xiao, Nicholas Dingwall, Xiaofei Ma, Andrew Arnold, Bing Xiang

Semantic Text Processing

Challenge:	Dialogue Sentence Embedding (DSE) is a self-supervised contrastive learning method that learns effective dialogue representations suitable for a wide range of dialogue-oriented tasks.
Approach:	They propose a self-supervised contrastive learning method that learns dialogue representations suitable for a wide range of dialogue tasks.
Outcome:	The proposed method outperforms baselines on five dialogue tasks on a few-shot and zero-shot datasets.

Hierarchical Inductive Transfer for Continual Dialogue Learning (2022.findings-acl)

Copied to clipboard

Shaoxiong Feng, Xuancheng Ren, Kan Li, Xu Sun

Stabilized In-Context Learning with Pre-trained Language Models for Few Shot Dialogue State Tracking (2023.findings-eacl)

Challenge:	Existing frameworks for learning and deployment of neural dialogue models have been used for online chit-chat scenarios.
Approach:	They propose a hierarchical inductive transfer framework to learn and deploy dialogue skills continually and efficiently.
Outcome:	The proposed framework achieves comparable performance under deployment-friendly model capacity.

Copied to clipboard

Derek Chen, Kun Qian, Zhou Yu

PFDial: A Structured Dialogue Instruction Fine-tuning Method Based on UML Flowcharts (2025.findings-acl)

Challenge:	Prompt-based methods with large pre-trained language models have shown impressive unaided performance across many NLP tasks.
Approach:	They propose a meta-learning scheme to stabilize the ability of the model to perform well under various prompts and introduce a saliency model to limit dialogue text length.
Outcome:	The proposed model improves on large pre-trained language models with labeled in-context exemplars and can be used to generate more exemplar queries.

Copied to clipboard

Ming Zhang, Yuhui Wang, Yujiong Shen, Tingyi Yang, Changhao Jiang, Yilong Wu, Shihan Dou, Qinhao Chen, Zhiheng Xi, Zhihao Zhang, Yi Dong, Zhen Wang, Zhihui Fei, Mingyang Wan, Tao Liang, Guojun Ma, Qi Zhang, Tao Gui, Xuanjing Huang

An Efficient Task-Oriented Dialogue Policy: Evolutionary Reinforcement Learning Injected by Elite Individuals (2025.acl-long)

Challenge:	Large Language Models (LLMs) have shown remarkable progress in dialogue and reasoning, but they struggle to solve strictly constrained dialogue tasks.
Approach:	They construct a dataset that contains 12,705 high-quality Chinese dialogue instructions from 440 flowcharts containing 5,055 process nodes.
Outcome:	The proposed model outperforms GPT-4o models on backward transitions and outperformed GPT-42 models on the same dataset.

Copied to clipboard

Yangyang Zhao, Ben Niu, Libo Qin, Shihan Wang

Leveraging Explicit Procedural Instructions for Data-Efficient Action Prediction (2023.findings-acl)

Challenge:	Evolutionary Algorithms (EAs) have been proven to effectively explore the solution space of neural networks by maintaining population diversity.
Approach:	They propose an elite individual injection mechanism to enhance EA’s search efficiency by adaptively introducing best-performing individuals into the population.
Outcome:	Experiments on four datasets show that the proposed approach significantly improves the balance between exploration and exploitation, boosting performance.

Copied to clipboard

Julia White, Arushi Raghuvanshi, Yada Pruksachatkun

EZCAT: an Easy Conversation Annotation Tool (2022.lrec-1)

Challenge:	a paper presents a data-efficient solution to constructing task-oriented dialogue systems . large language models have shown success in modeling such dialogues, but they require large quantities of data .
Approach:	They propose a system that leverages explicit instructions from agent guidelines . they propose dialogue-document matching and action-oriented masked language modeling .
Outcome:	The proposed system improves accuracy predicting in- and out-of-distribution actions while preserving high performance in settings with low or sparse data.

Copied to clipboard

Gaël Guibon, Luce Lefeuvre, Matthieu Labeau, Chloé Clavel

In-Context Learning for Few-Shot Dialogue State Tracking (2022.findings-emnlp)

Challenge:	EZCAT is an annotation tool for textual conversations, but it is not customizable.
Approach:	They propose an easy-to-use interface to annotate conversations in a configurable schema . they use it to annnotate private chats and chats, and they use the schema to test it .
Outcome:	The proposed interface allows users to control data and annotate conversations in two levels . it eliminates the need for a server and accounts management, and allows users access to data .

Copied to clipboard

Yushi Hu, Chia-Hsuan Lee, Tianbao Xie, Tao Yu, Noah A. Smith, Mari Ostendorf

Low-Resource NLP

Challenge:	Existing methods for zero-shot and few-shot learning dialogue state tracking are hard and expensive.
Approach:	They propose an in-context learning framework for zero-shot and few-shot learning dialogue state tracking (DST) a large pretrained language model takes a test instance and a few exemplars as input and directly decodes the dialogue state .
Outcome:	The proposed framework outperforms state-of-the-art models in few-shot settings . it is flexible and scalable, and requires less data to adapt to new domains and scenarios .

DialogBench: Evaluating LLMs as Human-like Dialogue Systems (2024.naacl-long)

Copied to clipboard

Jiao Ou, Junda Lu, Che Liu, Yihong Tang, Fuzheng Zhang, Di Zhang, Kun Gai

Task-Oriented Clustering for Dialogues (2021.findings-emnlp)

Challenge:	Existing benchmarks only evaluate LLMs' abilities for task completion as assistant AI.
Approach:	They propose a dialogue evaluation benchmark that contains 12 dialogue tasks to evaluate LLMs' capabilities as human-like dialogue systems.
Outcome:	The proposed benchmark contains 12 tasks to evaluate LLMs' capabilities . it shows that instruction tuning improves human likeness, but not as human-like systems .

Copied to clipboard

Chenxu Lv, Hengtong Lu, Shuyu Lei, Huixing Jiang, Wei Wu, Caixia Yuan, Xiaojie Wang

Don’t Say That! Making Inconsistent Dialogue Unlikely with Unlikelihood Training (2020.acl-main)

Challenge:	Existing methods for task-oriented dialogue clustering are difficult to apply directly due to inherent differences between them.
Approach:	They propose a Dialogue Task Clustering Network model for task-oriented clustering . they use context-aware utterance representations and cross-dialogue utterrance cluster representations .
Outcome:	The proposed model outperforms baselines on three public datasets on all metrics.

Copied to clipboard

Margaret Li, Stephen Roller, Ilia Kulikov, Sean Welleck, Y-Lan Boureau, Kyunghyun Cho, Jason Weston

I run as fast as a rabbit, can you? A Multilingual Simile Dialogues Datasets (2023.findings-acl)

Challenge:	Unlikelihood is a technique developed for removal of repetition in language model completions . it allows for a model to be generalized to solve a number of problems .
Approach:	They extend the unlikelihood objective to generate generations that contain repetitions . they show that such an objective can be used to improve logical consistency .
Outcome:	The proposed approach can be applied to a number of dialogue tasks.

Copied to clipboard

Longxuan Ma, Wei-Nan Zhang, Shuhan Zhou, Churui Sun, Changxin Ke, Ting Liu

Japanese Dialogue Corpus of Information Navigation and Attentive Listening Annotated with Extended ISO-24617-2 Dialogue Act Tags (L18-1)

Challenge:	A simile is a figure of speech that compares two different things via shared properties.
Approach:	They propose a multilingual simile dialogue dataset that can be used to study similes in real-life scenarios.
Outcome:	The proposed dataset is the largest manually annotated simile dataset and contains both English and Chinese data.

Copied to clipboard

Koichiro Yoshino, Hiroki Tanaka, Kyoshiro Sugiyama, Makoto Kondo, Satoshi Nakamura

Reason first, then respond: Modular Generation for Knowledge-infused Dialogue (2022.findings-emnlp)

Challenge:	Large-scale conventional dialogue corpora are mainly built for specified tasks with specially designed dialogue states.
Approach:	They propose to annotate large-scale dialogue data with an extended ISO-24617-2 dialogue act tag-set to model a natural conversation with machines.
Outcome:	The proposed corpus covers a wider range of dialogue tasks than existing task-oriented systems or text-chat systems.

Copied to clipboard

Leonard Adolphs, Kurt Shuster, Jack Urbanek, Arthur Szlam, Jason Weston

Training Neural Response Selection for Task-Oriented Dialogue Systems (P19-1)

Challenge:	Large language models can produce fluent dialogue but often hallucinate factual inaccuracies.
Approach:	They propose a modular model for incorporating knowledge into conversational agents that generates a knowledge sequence and then attends to its own generated knowledge sequence.
Outcome:	The proposed model hallucinates less in knowledge-grounded dialogue tasks and has advantages in terms of interpretability and modularity.

Copied to clipboard

Matthew Henderson, Ivan Vulić, Daniela Gerz, Iñigo Casanueva, Paweł Budzianowski, Sam Coope, Georgios Spithourakis, Tsung-Hsien Wen, Nikola Mrkšić, Pei-Hao Su

Hybrid Alignment Training for Large Language Models (2024.findings-acl)

Challenge:	Despite their popularity, retrieval-based models have had modest impact on task-oriented dialogue systems . main obstacle to their application is the low-data regime of most task-orientated dialogue tasks . e-commerce, banking, and other domains are applications of retrieval models .
Approach:	They propose a method which pretrains a retrieval-based model on large general-domain conversational corpora and fine-tunes it for the target dialogue domain.
Outcome:	The proposed method is evaluated on five diverse domains, ranging from e-commerce to banking.

Copied to clipboard

Chenglong Wang, Hang Zhou, Kaiyan Chang, Bei Li, Yongyu Mu, Tong Xiao, Tongran Liu, JingBo Zhu

PK-ICR: Persona-Knowledge Interactive Multi-Context Retrieval for Grounded Dialogue (2023.emnlp-main)

Challenge:	Existing approaches to align large language models with instructions and preferences are conflicting . et al., 2023b) show that hybrid alignment training can outperform baselines .
Approach:	They propose a hybrid alignment training approach based on alternating alignment and modified elastic weight consolidation methods to achieve better collaboration between different alignment tasks.
Outcome:	The proposed approach outperforms baseline alignment training methods on summarization and dialogue tasks.

Copied to clipboard

Minsik Oh, Joosung Lee, Jiwei Li, Guoyin Wang

PSYDIAL: Personality-based Synthetic Dialogue Generation Using Large Language Models (2024.lrec-main)

Challenge:	Identifying relevant persona or knowledge for conversational systems is difficult, but recent work has shown that it is more realistic to optimize for concrete persona.
Approach:	They propose a persona-knowledge dual context retrieval method that utilizes all dialogue contexts simultaneously.
Outcome:	The proposed method performs zero-shot top-1 knowledge retrieval and precise persona scoring.

Copied to clipboard

Ji-Eun Han, Jun-Seok Koh, Hyeon-Tae Seo, Du-Seong Chang, Kyung-Ah Sohn

Self-Explanation Prompting Improves Dialogue Understanding in Large Language Models (2024.lrec-main)

Challenge:	a new pipeline for personality-based synthetic dialogues is being developed in Korea . a dataset curated by large language models is needed to generate human-like dialogues .
Approach:	They propose a personality-based synthetic dialogue data pipeline to elicit responses from large language models via prompting.
Outcome:	The proposed pipeline generates human-like dialogues considering real-world scenarios when users engage with chatbots.

Copied to clipboard

Haoyu Gao, Ting-En Lin, Hangyu Li, Min Yang, Yuchuan Wu, Wentao Ma, Fei Huang, Yongbin Li

Responsible & Trustworthy NLP

Challenge:	Recent advances in large language models (LLMs) have achieved great success in various NLP tasks, but the vast model parameters pose challenges in downstream fine-tuning.
Approach:	They propose a task-agnostic prompting strategy that analyzes each dialogue utterance before task execution to enhance LLMs' comprehension in multi-turn dialogues.
Outcome:	The proposed strategy outperforms other zero-shot prompts and matches or exceeds efficacy of few-shot ones.

Dial HEALTHDIAL for Advice: A Multilingual and Multi-Parallel Spoken Dialogue Dataset for Knowledge-Grounded Information Seeking (2026.findings-acl)

Copied to clipboard

Songbo Hu, Yinhong Liu, Ej Zhou, Evgeniia Razumovskaia, Xiaobin Wang, Alexander Fraser, Ivan Vulić, Anna Korhonen

VisTW: Benchmarking Vision-Language Models for Taiwanese Mandarin in Taiwan (2026.findings-acl)

Challenge:	Creating spoken dialogue datasets is methodologically challenging due to the personally identifiable nature of speech signals.
Approach:	They propose a large-scale, multilingual, and multi-parallel dataset for developing and evaluating retrieval-augmented generation-based spoken dialogue systems.
Outcome:	The proposed dataset includes 6,000 information-seeking dialogues and 163 hours of user speech recorded from native speakers of four official WHO languages.

Copied to clipboard

Zhi Rui Tam, Yung-Yu Shih, Yen-Wei Lee, Ya-Ting Pai, Wen Yu Chang, Yun-Nung Chen

Real or Robotic? Assessing Whether LLMs Accurately Simulate Qualities of Human Responses in Human-LLM Dialogue (2026.findings-acl)

Challenge:	Vision-Language Models (VLMs) struggle in Taiwanese Mandarin environments due to region-specific orthographic and cultural context.
Approach:	They propose a human-grounded purity penalty for character mixing under Taiwanese-Mandarin-style prompts.
Outcome:	The proposed model outperforms the strongest open-weight baseline by 22 percentage points on dialogue tasks.

Copied to clipboard

Jonathan Ivey, Shivani Kumar, Jiayu Liu, Hua Shen, Sushrita Rakshit, Rohan Raju, Haotian Zhang, Aparna Ananthasubramaniam, Junghwan Kim, Bowen Yi, Dustin Wright, Abraham Israeli, Anders Giovanni Møller, Lechen Zhang, David Jurgens