Papers by Junfeng Jiang

18 papers
TC–RAG: Turing–Complete RAG’s Case study on Medical LLM Systems (2025.acl-long)

Copied to clipboard

Challenge: Existing approaches to RAG neglect system state variables, resulting in poor performance and erroneous knowledge accumulation.
Approach: They propose a framework that incorporates a Turing Complete System to manage state variables and manage retrieval halting.
Outcome: The proposed framework improves on seven real-world healthcare datasets and shows that it is more accurate than existing methods.
SuperDialseg: A Large-scale Dataset for Supervised Dialogue Segmentation (2023.emnlp-main)

Copied to clipboard

Challenge: Empirical studies show that supervised learning is extremely effective in in-domain datasets and models trained on SuperDialseg can achieve good generalization ability on out-of-domain data.
Approach: They propose a supervised definition of dialogue segmentation points using document-grounded dialogues and a large-scale supervised dataset called SuperDialseg.
Outcome: The proposed model can achieve good generalization ability on out-of-domain data.
Attention-based Relational Graph Convolutional Network for Target-Oriented Opinion Words Extraction (2021.eacl-main)

Copied to clipboard

Challenge: empirical results show that our model significantly outperforms all existing models on four benchmark datasets.
Approach: They propose a novel attention-based relational graph convolutional neural network to exploit syntactic information over dependency graphs.
Outcome: The proposed model outperforms existing models on four benchmark datasets.
MED-COREASONER: Reducing Language Disparities in Medical Reasoning via Language-Informed Co-Reasoning (2026.acl-long)

Copied to clipboard

Challenge: Existing models that use English and local languages have a multilingual gap . a language-informed co-reasoning framework can be used to improve multilingual reasoning .
Approach: They propose a language-informed co-reasoning framework that elicits parallel English and local-language reasoning and abstracts them into structured concepts.
Outcome: Experiments show that Med-CoReasoner improves multilingual reasoning performance by 5% . the framework produces clinically sound and culturally grounded reasoning traces .
Multimodal Large Language Models for Text-rich Image Understanding: A Comprehensive Review (2025.findings-acl)

Copied to clipboard

Challenge: Recent advances in vision-language models have unified perception and understanding tasks within Visual Question Answering paradigms.
Approach: They propose to outline timeline, architecture, and pipeline of nearly all TIU MLLMs and review their performance on mainstream benchmarks.
Outcome: The proposed models perform well on mainstream benchmarks and are compared with other models.
3DS: Medical Domain Adaptation of LLMs via Decomposed Difficulty-based Data Selection (2025.emnlp-main)

Copied to clipboard

Challenge: Effective domain adaptation typically involves supervised fine-tuning on carefully selected instruction-tuned data.
Approach: They propose a model-centric data selection framework that aligns data selection with the model’s knowledge distribution to improve model performance.
Outcome: The proposed framework outperforms existing methods by up to 2.97% accuracy in the healthcare domain.
PQR: Improving Dense Retrieval via Potential Query Modeling (2025.acl-long)

Copied to clipboard

Challenge: Existing training data is sparse, with each document associated with one or a few labeled queries.
Approach: They propose a training-free potential query retrieval framework to address this problem . they use a Gaussian mixture distribution to model all potential queries for a document .
Outcome: The proposed method is able to capture comprehensive semantic information from a document with multiple queries.
HyKGE: A Hypothesis Knowledge Graph Enhanced RAG Framework for Accurate and Reliable Medical LLMs Responses (2025.acl-long)

Copied to clipboard

Challenge: Recent approaches suffer from insufficient and repetitive knowledge retrieval, tedious and time-consuming query parsing, and monotonous knowledge utilization.
Approach: They propose a retrieval-augmented generation framework which leverages LLMs’ powerful reasoning capacity to compensate for the incompleteness of user queries.
Outcome: The proposed framework improves the accuracy and reliability of Large Language Models (LLMs) by combining the rich knowledge of LLMs with Hypothesis Outputs.
What Language Do Non-English-Centric Large Language Models Think in? (2025.findings-acl)

Copied to clipboard

Challenge: Despite their robust performance in English, these models often exhibit reduced proficiency in non-English languages, and their outputs may reflect an inherent bias toward English-centric perspectives.
Approach: They categorize non-English-centric large language models into two groups: CPMs and BLMs, which are pre-trained on a balanced mix of multiple languages from scratch.
Outcome: The proposed models exhibit a pronounced internal preference for English tokens when projected into the vocabulary space.
JMedBench: A Benchmark for Evaluating Japanese Biomedical Large Language Models (2025.coling-main)

Copied to clipboard

Challenge: Existing large language models (LLMs) focus on general domains, with fewer advancements in Japanese biomedical LLMs.
Approach: They propose a benchmark for Japanese large language models with eight LLMs across four categories and 20 Japanese biomedical datasets for comparison.
Outcome: The proposed benchmark includes eight LLMs across four categories and 20 Japanese biomedical datasets across five tasks.
Parenting: Optimizing Knowledge Selection of Retrieval-Augmented Language Models with Parameter Decoupling and Tailored Tuning (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for integrating internal and external knowledge lack effective control mechanisms for generating hallucinations and dealing with outdated knowledge.
Approach: They propose a framework that decouples, identifies, and purposefully optimizes parameter subspaces related to adherence and robustness.
Outcome: The proposed framework decouples, identifies, and purposefully optimizes parameter subspaces related to adherence and robustness.
Generative Data Augmentation for Aspect Sentiment Quad Prediction (2023.starsem-1)

Copied to clipboard

Challenge: Existing approaches to analyze text contain rewrites and inconsistency between text and quads.
Approach: They propose a new approach to analyze aspect terms, opinion terms, sentiment polarity in text . they augment quads and train a quads-to-text model to generate corresponding texts .
Outcome: The proposed method outperforms existing methods and achieves state-of-the-art performance on two datasets.
Dial2vec: Self-Guided Contrastive Learning of Unsupervised Dialogue Embeddings (2022.emnlp-main)

Copied to clipboard

Challenge: Dialogue embeddings are a critical prerequisite for semantically understanding dialogues.
Approach: They propose a self-guided contrastive learning approach called dial2vec that captures interaction patterns between interlocutors and leverages them to guide the learning of the embeddings corresponding to each interlocuter.
Outcome: The proposed approach achieves 8.7, 9.0, and 13.8 points absolute improvements over the strongest baseline on the three evaluation tasks respectively.
Improving Referring Ability for Biomedical Language Models (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing auto-regressive large language models (LLMs) are primarily trained using documents from general domains.
Approach: They propose to use citation network to improve the pre-training of auto-regressive large language models (LLMs) in the biomedical domain.
Outcome: Empirical studies show that the proposed method improves both the intra-sample and inter-sammple referring abilities of auto-regressive large language models in the biomedical domain.
DFAMS: Dynamic-flow guided Federated Alignment based Multi-prototype Search (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for ambiguous queries struggle to retrieve high-quality documents . DFAMS outperforms advanced FR methods by 14.37% in knowledge classification accuracy .
Approach: They propose a framework that leverages dynamic information flow to identify latent query intents and construct semantically aligned knowledge partitions for accurate retrieval across heterogeneous sources.
Outcome: The proposed framework outperforms existing methods in classification accuracy and retrieval recall tests.
Leveraging High-Resource English Corpora for Cross-lingual Domain Adaptation in Low-Resource Japanese Medicine via Continued Pre-training (2025.findings-emnlp)

Copied to clipboard

Challenge: low-resource language corpora in professional domains like medicine hinder cross-lingual domain adaptation of pre-trained large language models.
Approach: They examine how linguistic features affect performance on a Japanese–English medical knowledge benchmark.
Outcome: The proposed model can leverage English-language resources in medical domains while ensuring sufficient coverage of language-specific expressions in a target language.
ProMed: Shapley Information Gain Guided Reinforcement Learning for Proactive Medical LLMs (2026.acl-long)

Copied to clipboard

Challenge: Existing medical Large Language Models (LLMs) follow a reactive paradigm, risking diagnostic errors by answering before seeking sufficient details.
Approach: They propose a reinforcement learning framework that transitions LLMs toward a proactive paradigm, enabling them to ask clinically valuable questions before decision-making.
Outcome: Experiments on partial-information medical benchmarks show that ProMed outperforms state-of-the-art methods by 6.29% on average and delivers a 54.45% gain over the reactive paradigm.
Neuron-Level Sequential Editing for Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Existing model editing methods focus on single-round editing and often face significant challenges in sequential model editing.
Approach: They propose a model editing method that optimizes the target layer’s hidden states using the model’s original weights to prevent model failure.
Outcome: The proposed method outperforms existing model editing methods and is available on the open-source platform 4open.science.

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