Papers by Junlan Feng

Log-FGAER: Logic-Guided Fine-Grained Address Entity Recognition from Multi-Turn Spoken Dialogue (2023.emnlp-main)

Challenge:	a novel multi-task learning framework for domain-specific natural language understanding tasks addresses these limitations by combing multiple tasks into a single framework.
Approach:	They propose a multi-task learning framework that decomposes the language model into modular skill components and employs a dynamic, learnable skill-combination mechanism to adaptively handle diverse tasks.
Outcome:	The proposed framework surpasses conventional multi-task learning approaches in performance.

Copied to clipboard

Xue Han, Yitong Wang, Qian Hu, Pengwei Hu, Chao Deng, Junlan Feng

Named Entity Recognition

Challenge:	Existing name entity recognition methods combine pre-trained language models with supervised models such as BiLSTM/LSTM-CRF to perform poorly in a spoken dialogue context.
Approach:	They propose a logic-guided fine-grained address recognition method that softly applies the logic rule to improve the accuracy of FGAER.
Outcome:	The proposed method improves fine-grained address entity recognition from multi-turn spoken dialogues.

From Superficial to Deep: Integrating External Knowledge for Follow-up Question Generation Using Knowledge Graph and LLM (2025.coling-main)

Copied to clipboard

Jianyu Liu, Yi Huang, Sheng Bi, Junlan Feng, Guilin Qi

Knowledge Representation

Challenge:	Existing methods for generating follow-up questions are limited to shallow contextual questions that are uninspiring and have a large gap to the human level.
Approach:	They propose a three-stage external knowledge-enhanced follow-up question generation method which generates questions by identifying contextual topics, building a knowledge graph online, and finally combining these with a large language model to generate the final question.
Outcome:	The proposed method generates questions by identifying contextual topics, building a knowledge graph (KG) online, and finally combining these with a large language model to generate the final question.

Generalized Intent Discovery: Learning from Open World Dialogue System (2022.coling-1)

Copied to clipboard

Yutao Mou, Keqing He, Yanan Wu, Pei Wang, Jingang Wang, Wei Wu, Yi Huang, Junlan Feng, Weiran Xu

A Probabilistic End-To-End Task-Oriented Dialog Model with Latent Belief States towards Semi-Supervised Learning (2020.emnlp-main)

Challenge:	Existing intent classification models rely on a pre-defined intent set and supervised labels, which is limited in some practical scenarios.
Approach:	They propose to extend an IND intent classifier to an open-world intent set including IND and OOD intents.
Outcome:	The proposed task can classify IND and OOD intents while discovering new unlabeled OOD types incrementally.

Copied to clipboard

Yichi Zhang, Zhijian Ou, Min Hu, Junlan Feng

Responsible & Trustworthy NLP

Challenge:	Structured belief states are crucial for goal tracking and database query in task-oriented dialog systems.
Approach:	They propose a probabilistic dialog model where belief states are represented as discrete latent variables and jointly modeled with system responses given user inputs.
Outcome:	The proposed model outperforms supervised-only and semi-supervised baselines on three benchmark datasets.

PSSAT: A Perturbed Semantic Structure Awareness Transferring Method for Perturbation-Robust Slot Filling (2022.coling-1)

Copied to clipboard

Guanting Dong, Daichi Guo, Liwen Wang, Xuefeng Li, Zechen Wang, Chen Zeng, Keqing He, Jinzheng Zhao, Hao Lei, Xinyue Cui, Yi Huang, Junlan Feng, Weiran Xu

Robustness in NLP

Challenge:	Existing slot filling models memorize inherent patterns of entities and contexts from training data.
Approach:	They propose a perturbed semantic structure awareness transferring method for slot filling models . they use two MLM-based training strategies to learn contextual semantic structure and word distribution .
Outcome:	The proposed method outperforms existing methods and gains strong generalization while preventing model from memorizing inherent patterns of entities and contexts.

D2PCM:A Multi-Turn Dialogue Dataset with Personalized Contextual Memory (2026.findings-acl)

Copied to clipboard

Zhe Yang, Yi Huang, Yaqin Chen, Chunyang Gao, Jingyu Yao, Junlan Feng

Investigating and Scaling up Code-Switching for Multilingual Language Model Pre-Training (2025.findings-acl)

Challenge:	Conventional interactive algorithms have predominantly treated memory as a contextual element, neglecting the nuanced cognitive processes involved in individualized memory encoding and retrieval.
Approach:	They propose a multi-turn dialogue dataset with Personalized Contextual Memory to facilitate advanced research on personalized memory processing.
Outcome:	The proposed datasets provide a comprehensive benchmark to facilitate advanced research on personalized memory processing.

Copied to clipboard

Zhijun Wang, Jiahuan Li, Hao Zhou, Rongxiang Weng, Jingang Wang, Xin Huang, Xue Han, Junlan Feng, Chao Deng, Shujian Huang

Multilinguality

Challenge:	Large language models (LLMs) exhibit remarkable multilingual capabilities despite the extreme language imbalance in the pre-training data.
Approach:	They investigate the existence of code-switching in the pre-training corpus and categorize it into four types within two quadrants.
Outcome:	The proposed approach improves performance across benchmarks and representation space.

MultiPL-MoE: Multi-Programming-Lingual Extension of Large Language Models through Hybrid Mixture-of-Experts (2025.findings-emnlp)

Copied to clipboard

Qing Wang, Xue Han, Jiahui Wang, Lehao Xing, Qian Hu, Lianlian Zhang, Chao Deng, Junlan Feng

Multimodality

Challenge:	MultiPL is a special case of multiple natural languages and requires limited computational resources to generate multilingual code.
Approach:	They propose to extend LLMs by combining two paired experts to optimize expert selection at token and segment levels.
Outcome:	The proposed extension improves the performance of the base LLMs while retaining the most popular ones using limited computational resources.

Meta-Reinforced Multi-Domain State Generator for Dialogue Systems (2020.acl-main)

Copied to clipboard

Yi Huang, Junlan Feng, Min Hu, Xiaoting Wu, Xiaoyu Du, Shuo Ma

A structure-enhanced graph convolutional network for sentiment analysis (2020.findings-emnlp)

Challenge:	Existing methods to train a multi-domain dialogue state tracker are lacking in accuracy.
Approach:	They propose a Meta-Reinforced Multi-Domain State Generator to train a DST meta-learning model with a few domains as source domains and a new domain as target domain.
Outcome:	The proposed system outperforms the traditional training approach with extremely little training data in target domain.

Copied to clipboard

Fanyu Meng, Junlan Feng, Danping Yin, Si Chen, Min Hu

Syntactic Text Processing

Challenge:	Recent work on sentiment analysis and aspect-based sentiment analysis does not exploit syntactic information from dependency parsing.
Approach:	They propose a weighted graph convolutional network which exploits syntactic information . they use BERT instead of Bi-LSTM to generate contextualized representations as inputs .
Outcome:	The proposed model can exploit rich syntactic information based on feature combination . it can improve on four ABSA tasks out of six and two SA tasks out .

Towards Low-Resource Semi-Supervised Dialogue Generation with Meta-Learning (2020.findings-emnlp)

Copied to clipboard

Yi Huang, Junlan Feng, Shuo Ma, Xiaoyu Du, Xiaoting Wu

Large Language Models Are Cross-Lingual Knowledge-Free Reasoners (2025.naacl-long)

Challenge:	Existing systems that use labelled data to generate dialogues are lacking in high accuracy.
Approach:	They propose a meta-learning based semi-supervised explicit dialogue state tracker for neural dialogue generation, denoted as MEDST.
Outcome:	The proposed system outperforms existing systems by 18.7% goal accuracy and 14.3% entity match rate on the KVRET corpus with 2% labelled data in semi-supervision.

Copied to clipboard

Peng Hu, Sizhe Liu, Changjiang Gao, Xin Huang, Xue Han, Junlan Feng, Chao Deng, Shujian Huang

Palette of Language Models: A Solver for Controlled Text Generation (2025.naacl-long)

Challenge:	Large language models have demonstrated impressive reasoning capabilities across multiple languages, but the relationship between capabilities in different languages is less explored.
Approach:	They decompose the process of reasoning tasks into two separate components: knowledge retrieval and knowledge-free reasoning.
Outcome:	The proposed model can be transferred across source-target languages despite secondary impact of resource in some specific target languages, while cross-lingual knowledge retrieval significantly hinders the transfer.

Copied to clipboard

Zhe Yang, Yi Huang, Yaqin Chen, XiaotingWu XiaotingWu, Junlan Feng, Chao Deng

Soft Orthogonal Low-Rank Adaptation for Knowledge Sharing in Large Language Model Continual Learning (2026.acl-long)

Challenge:	Recent advances in large language models have revolutionized text generation with their remarkable capabilities.
Approach:	They propose to combine a single-attribute model with a discriminative model to achieve a combination strategy that incorporates positive correlation and attribute enhancement.
Outcome:	The proposed method is adapted for single-attribute control scenario and achieves surpassing results.

Copied to clipboard

Yitong Wang, Xue Han, WenChun Gao, Qian Hu, Jiahui Wang, Ziqing Wang, Lijun Mei, Junlan Feng

Thinking-Based Non-Thinking: Solving the Reward Hacking Problem in Training Hybrid Reasoning Models via Reinforcement Learning (2026.acl-long)

Challenge:	Existing methods for continual learning (CL) are designed to mitigate catastrophic forgetting while neglecting knowledge sharing across tasks.
Approach:	They propose a framework that facilitates knowledge transfer while mitigating catastrophic forgetting by assigning task-specific parameter subspaces to new tasks . they then leverage attribution scores to evaluate task similarity and employ soft orthogonality between task- specific subspace .
Outcome:	The proposed framework facilitates knowledge transfer while mitigating catastrophic forgetting.

Copied to clipboard

Siyuan Gan, Jiaheng Liu, Boyan Wang, Tianpei Yang, Runqing Miao, Yuyao Zhang, Fanyu Meng, Junlan Feng, Linjian Meng, Jing Huo, Yang Gao

PEGRL: Improving Machine Translation by Post-Editing Guided Reinforcement Learning (2026.findings-acl)

Challenge:	Existing work on large reasoning models (LRMs) focuses on using reinforcement learning (RL) to train hybrid reasoning models that automatically decide whether to engage in thinking or not based on the complexity of the query.
Approach:	They propose to use reinforcement learning to train hybrid reasoning models that automatically decide whether to engage in thinking or not based on the complexity of the query.
Outcome:	The proposed model reduces token usage by around 50%$ compared to DeepSeek-R1-Distill-Qwen-1.5B/7B and DeepScaleR-1.5b, while significantly improving accuracy.

Copied to clipboard

Yunzhi Shen, Hao Zhou, Xin Huang, Xue Han, Junlan Feng, Shujian Huang

LLM as a metric critic for low resource relation identification (2024.findings-emnlp)

Challenge:	Reinforcement learning (RL) has shown strong promise for LLM-based machine translation . however, translation-oriented RL remains challenged by high-variance policy gradients induced by Monte Carlo baselines and large trajectory space that favors global exploration over fine-grained local optimization.
Approach:	They propose a two-stage RL framework that uses post-editing as an auxiliary task to stabilize training and guide overall optimization.
Outcome:	The proposed framework supports global exploration and fine-grained optimization while supporting global exploration.

Copied to clipboard

Zhe Yang, Yi Huang, Yaqin Chen, Xiaoting Wu, Junlan Feng, Chao Deng

Information Retrieval

Challenge:	Existing studies show that small language models (SLMs) overfit in low resource situations . however, the gap between pre-training and fine-tuning leads to performance decay .
Approach:	They propose to combine large language models and LLM for relation identification by co-evolution . they propose to use a masked language model prompt to generate a relation identification task .
Outcome:	The proposed model can handle low resource relation identification tasks with minimal overfitting . the proposed model provides essential background knowledge to assist training process .

Cognitive Alpha Mining via LLM-Driven Code-Based Evolution (2026.acl-long)

Copied to clipboard

Fengyuan Liu, Yi Huang, Sichun Luo, Yuqi Wang, Yazheng Yang, Xinye Li, Zefa Hu, Junlan Feng, Qi Liu

Beyond Static Profiles: Capturing the Fluidity of User Preferences in Diverse Scenarios (2026.findings-acl)

Challenge:	Existing approaches to finding effective predictive signals from financial data are limited by their complexity and low signal-to-noise ratio.
Approach:	They propose a framework that combines code-level alpha representation with LLM-driven reasoning and evolutionary search.
Outcome:	The proposed framework combines code-level alpha representation with LLM-driven reasoning and evolutionary search.

Copied to clipboard

Chunyang Gao, Yi Huang, Jingyu Yao, Xiaoting Wu, Junlan Feng

Challenge:	Existing approaches to personalize Large Language Models often default to homogeneous behaviors . preferences can shift, and conflict, depending on context, authors argue .
Approach:	They propose a hierarchical taxonomy to differentiate between stable and situational preferences . they use a dataset of 10k meticulously curated preferences to test their taxonomies .
Outcome:	The proposed model differentiates between stable and situational preferences based on curated user preferences . it provides a practical testbed for advancing dynamic, context-aware personalization in conversational agents.

Entriever: Energy-based Retriever for Knowledge-Grounded Dialog Systems (2025.findings-acl)

Copied to clipboard

Yucheng Cai, Ke Li, Yi Huang, Junlan Feng, Zhijian Ou

Information Retrieval

Challenge:	Existing knowledge retrieval methods fail to account for interrelationship between knowledge pieces . however, current methods fail in a situation where multiple knowledge pieces are relevant .
Approach:	They propose an energy-based retriever that directly models the candidate retrieval results as a whole instead of modeling the knowledge pieces separately.
Outcome:	The proposed retriever outperforms the baseline energy-based retriever in knowledge retrieval tasks.

Understanding LLMs’ Cross-Lingual Context Retrieval: How Good It Is And Where It Comes From (2025.emnlp-main)

Copied to clipboard

Changjiang Gao, Hankun Lin, Xin Huang, Xue Han, Junlan Feng, Chao Deng, Jiajun Chen, Shujian Huang

Cross-Lingual Transfer

Challenge:	Cross-lingual context retrieval is a fundamental aspect of cross-lingual alignment, but the performance and mechanism of it for large language models (LLMs) remains unclear.
Approach:	They evaluate cross-lingual context retrieval of over 40 large language models . they use cross-linguistic machine reading comprehension as a representative scenario .
Outcome:	The results show that open LLMs show strong cross-lingual context retrieval ability . the results also show that their oracle performances improve after training .

Learning to Leverage High-Order Medical Knowledge Graph for Joint Entity and Relation Extraction (2023.findings-acl)

Copied to clipboard

Zhe Yang, Yi Huang, Junlan Feng

Information Extraction & Text Mining

Challenge:	Medical terms are difficult to understand and relations between medical entities become complicated.
Approach:	They propose to leverage medical domain knowledge for extracting entities and relations for Chinese medical texts by building a heterogeneous graph based on medical knowledge graph.
Outcome:	The proposed method is more effective than state-of-the-art methods on real Chinese medical texts.

AlphaQT-Bench: Diagnosing the Gap between Financial Code Generation and Quantitative Reasoning in LLMs (2026.findings-acl)

Copied to clipboard

Sichun Luo, Yi Huang, Shichang Meng, Fengyuan Liu, Mukai Li, Qinghua Yao, Zefa Hu, Junlan Feng, Qi Liu

Programming Languages in NLP

Challenge:	Existing benchmarks rely on outcome-driven metrics such as profitability and look-ahead bias.
Approach:	They propose a diagnostic benchmark for instruction-grounded financial code generation under strict semantic and temporal constraints.
Outcome:	The proposed benchmarks show that the models fail under causal, structural, or functional constraints.

Self-attention-based Graph-of-Thought for Math Problem Solving (2025.findings-acl)

Copied to clipboard

Ruiqiao Bai, Xue Han, Shuo Lei, Junlan Feng, Yanyan Luo, Chao Deng

Thinking Alignment of Scenario-Oriented User Simulation (2026.acl-long)

Challenge:	Existing methods for generating reasoning paths in a chain structure are inefficient and non-human-like.
Approach:	They propose a decoding method for a chain-based LLM that constructs a thought graph simultaneously as an LLM inference and generates reasoning steps with a graph-structured self-attention mechanism.
Outcome:	The proposed method improves reasoning accuracy without huge computational over-expensive LLMs and avoids performance degradation issues when the LLM is too small to comprehend complex prompts.

Copied to clipboard

Xiaoting Wu, Yi Huang, Chunyang Gao, Mengfei Guo, Jingyu Yao, Junlan Feng

Beyond Layout Embedding: Layout Attention with Gaussian Biases for Structured Document Understanding (2023.findings-emnlp)

Challenge:	Existing user simulators based on prompting to role-play or SFT focus on imitating textual utterances without considering multi-faceted cognitive processes that underlie human decision-making during interactions.
Approach:	They construct a user-simulator dataset that augments 51k human–LLM conversations by reconstructing the user’s inner reasoning during and at the end of each dialogue.
Outcome:	The proposed user simulators augment 51k human–LLM conversations by reconstructing the user’s inner reasoning both during and at the end of each dialogue.

Copied to clipboard

Xi Zhu, Xue Han, Shuyuan Peng, Shuo Lei, Chao Deng, Junlan Feng

Representation Learning

Challenge:	Existing methods for encoding layout information rely on millions of learnable parameters . polar coordinates provide superior choice for layout modeling, study finds .
Approach:	They propose to model layout attention with Gaussian biases by feeding polar coordinates into 2-D Gausssian kernels.
Outcome:	The proposed model improves on three widely used benchmarks.

ChildEval:WHEN LARGE LANGUAGE MODELS MEET CHILDREN’S PERSONALITIES (2026.findings-acl)

Copied to clipboard

Yanyan Luo, Xue Han, Chunxu Zhao, Ruiqiao Bai, Yaxing Zhang, Qian Hu, Lijun Mei, Junlan Feng