Papers by Kun Qian

19 papers
Domain Adaptive Dialog Generation via Meta Learning (P19-1)

Copied to clipboard

Challenge: Existing methods to adapt dialog data to new domains with limited resources are expensive . a domain adaptive dialog system model learns from multiple rich-resource tasks and adapts to new tasks with minimal training samples.
Approach: They propose a domain adaptive dialog generation method based on meta-learning . they train a dialog system model using multiple rich-resource single-domain dialog data .
Outcome: The proposed method can learn a competitive dialog system on a new domain with minimal training examples.
MAKAR: a Multi-Agent framework based Knowledge-Augmented Reasoning for Grounded Multimodal Named Entity Recognition (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods for GMNER fail to address semantic ambiguity caused by polysemy and long-tail distribution of datasets.
Approach: They propose a framework for Grounded Multimodal Named Entity Recognition that leverages a Multimodal Large Language Model to address semantic ambiguity.
Outcome: Extensive experiments show that the proposed framework outperforms existing methods on two benchmark datasets.
FLEEK: Factual Error Detection and Correction with Evidence Retrieved from External Knowledge (2023.emnlp-demo)

Copied to clipboard

Challenge: Existing large language models (LLMs) have a tendency to hallucinate and provide creative and fluent responses that are not factually accurate.
Approach: They propose a tool that automatically extracts factual claims from text, gathers evidence from external knowledge sources, evaluates the factuality of each claim, and suggests revisions for identified errors.
Outcome: The proposed tool detects errors in text and evaluates their factuality and suggests revisions based on the collected evidence.
KRLS: Improving End-to-End Response Generation in Task Oriented Dialog with Reinforced Keywords Learning (2023.emnlp-main)

Copied to clipboard

Challenge: Task-oriented dialogs (TOD) require a model to generate a response that optimizes for task-related metrics.
Approach: They propose a faster generation procedure that samples from independent next-word distributions and introduce a fine-grained reward function to help the model focus on learning key information in a dialog.
Outcome: The proposed algorithm achieves state-of-the-art performance on an offline task with 15% training time reduction compared to a standard RL algorithm using auto-regressive generation.
Learning Structured Representations of Entity Names using Active Learning and Weak Supervision (2020.emnlp-main)

Copied to clipboard

Challenge: Structured representations of entity names are useful for many entity-related tasks such as entity normalization and variant generation.
Approach: They propose a framework that combines active learning and weak supervision to solve this problem.
Outcome: The proposed framework enables learning of high-quality models from a dozen labeled examples.
AgentThink: A Unified Framework for Tool-Augmented Chain-of-Thought Reasoning in Vision-Language Models for Autonomous Driving (2025.findings-emnlp)

Copied to clipboard

Challenge: Vision-Language Models struggle with hallucinations, inefficient reasoning, and limited real-world validation hinders accurate perception and robust step-by-step reasoning.
Approach: AgentThink integrates Chain-of-Thought reasoning with dynamic, agent-style tool invocation for autonomous driving tasks.
Outcome: Experiments on the DriveLMM-o1 benchmark show AgentThink significantly boosts overall reasoning scores by 53.91% and enhances answer accuracy by 33.54% .
Database Search Results Disambiguation for Task-Oriented Dialog Systems (2022.naacl-main)

Copied to clipboard

Challenge: Task-oriented dialog systems can't handle multiplesearch results when querying a database due to the lack of such scenarios in existing datasets.
Approach: They propose a task that focuses on disambiguating database search results by synthetically generating turns through a pre-defined grammar and collecting human paraphrases for a subset.
Outcome: The proposed task improves performance on DSR-disambiguation even in the absence of in-domain data, suggesting it can be learned as a universal dialog skill.
DialogStudio: Towards Richest and Most Diverse Unified Dataset Collection for Conversational AI (2024.findings-eacl)

Copied to clipboard

Challenge: DialogStudio is the largest and most diverse collection of dialogue datasets . existing datasets lack diversity and comprehensiveness, authors say .
Approach: They introduce DialogStudio: the largest and most diverse collection of dialogue datasets . DialogStuio aggregates more than 80 diverse dialogue dataset .
Outcome: a new dataset is created to improve the quality and diversity of dialogue datasets . DialogStudio is the largest and most diverse collection of dialogue data .
DECOR: Improving Coherence in L2 English Writing with a Novel Benchmark for Incoherence Detection, Reasoning, and Rewriting (2024.emnlp-main)

Copied to clipboard

Challenge: Existing automated writing evaluation systems only detect incoherence in writing . a recent study has found that incorporating specific reasons for incohence improves the quality of rewrites .
Approach: They propose a benchmark that includes expert annotations for detecting incoherence in L2 English writing, identifying the underlying reasons, and rewriting the incoerent sentences.
Outcome: The proposed benchmark improves coherence in L2 English writing by fine-tuning models . the authors find that incorporating specific reasons improves quality of rewrites .
Time Sensitive Knowledge Editing through Efficient Finetuning (2024.acl-short)

Copied to clipboard

Challenge: Existing locate-and-edit knowledge editing methods suffer from two limitations: they are infeasible for large scale KE in practice and require long run-time.
Approach: They propose to use parametric fine-tuning techniques to update obsolete knowledge and induce new knowledge into LLMs.
Outcome: The proposed methods improve the performance of KE and knowledge update in a temporal dataset with knowledge update and knowledge injection examples.
How to Build User Simulators to Train RL-based Dialog Systems (D19-1)

Copied to clipboard

Challenge: RL-based dialog systems require interaction with the environment and obtaining real human users to interact with the system is time-consuming and labor-intensive.
Approach: They propose a method to standardize user simulator building to compare dialog system quality using the same set of user simulators.
Outcome: The proposed method can be used by the community to compare dialog system quality using the same set of user simulators fairly.
Memformer: A Memory-Augmented Transformer for Sequence Modeling (2022.findings-aacl)

Copied to clipboard

Challenge: Experimental results show that Memformer uses 8.1x less memory space and 3.2x faster on inference.
Approach: They propose an efficient neural network that utilizes an external dynamic memory to encode and retrieve past information.
Outcome: The proposed model achieves comparable performance against baselines with 8.1x less memory space and 3.2x faster on inference.
Bottom-Up Synthesis of Knowledge-Grounded Task-Oriented Dialogues with Iteratively Self-Refined Prompts (2025.naacl-short)

Copied to clipboard

Challenge: Training conversational question-answering systems requires in-domain data, which is often scarce in practice.
Approach: They propose a bottom-up approach where QA pairs are generated first and combined into a coherent dialogue.
Outcome: The proposed approach produces more realistic and higher-quality dialogues compared to top-down methods.
Stabilized In-Context Learning with Pre-trained Language Models for Few Shot Dialogue State Tracking (2023.findings-eacl)

Copied to clipboard

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.
Reinforcing Agentic Search Via Reward Density Optimization (2026.acl-long)

Copied to clipboard

Challenge: Reinforcement Learning with Verifiable Rewards (RLVR) is a promising approach for enhancing agentic search, but its performance is often hindered by reward sparsity .
Approach: They propose a new research problem to improve the reward obtained per unit of exploration cost by using a system that decomposes long-horizon tasks into intermediate objectives and assigns process-level rewards to provide denser learning signals.
Outcome: The proposed framework outperforms strong baselines on several agentic search benchmarks and achieves comparable performance to that of advanced proprietary models.
A Survey of the State of Explainable AI for Natural Language Processing (2020.aacl-main)

Copied to clipboard

Challenge: Recent years have seen significant advances in the quality of state-of-the-art models, but they have come at the expense of models becoming less interpretable.
Approach: This survey examines the current state of Explainable AI within the domain of NLP . they detail the operations and explainability techniques currently available for generating explanations for NLP models .
Outcome: This survey examines the state of explainable AI (XAI) within the domain of natural language processing . it focuses on the operations and explainability techniques currently available for NLP models .
Low-resource Deep Entity Resolution with Transfer and Active Learning (P19-1)

Copied to clipboard

Challenge: Entity resolution (ER) is the task of identifying different representations of the same real-world entities across databases.
Approach: They propose a deep learning-based method that targets low-resource settings for ER by combining transfer learning and active learning.
Outcome: The proposed method achieves comparable, if not better, performance compared to state-of-the-art learning-based methods while using an order of magnitude fewer labels.
Exploiting Structure in Representation of Named Entities using Active Learning (C18-1)

Copied to clipboard

Challenge: Named entities are atomic objects of reference and reasoning in many knowledge-centric applications.
Approach: They propose an active-learning based framework that drastically reduces the labeled data required to learn entities' structures.
Outcome: The proposed framework outperforms handwritten programs and supervised learning models in relation extraction and entity resolution tasks.
VarBench: Robust Language Model Benchmarking Through Dynamic Variable Perturbation (2024.findings-emnlp)

Copied to clipboard

Challenge: Recent benchmarks release only training and validation sets, keeping the test set labels closed-source.
Approach: They propose to extract variables from each test case and define a value range for each variable.
Outcome: The proposed method improves the accuracy of the evaluations on four datasets covering mathematical generation and multiple-choice tasks.

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