Papers by Min Song

An Empirical Study of Iterative Refinements for Non-autoregressive Translation (2025.acl-long)

Challenge:	Existing methods focus on replicating dialogues in textual form, neglecting the role’s voice traits as a crucial effect in interaction, which tends to be more immersive experiences in realistic scenarios.
Approach:	They propose a first seamless speech-language personality interaction model to achieve immersive RPAs with low latency.
Outcome:	The proposed model exhibits role-specific personality traits and vocal traits throughout the interaction, enabling a mixture of speech and language responses.

Copied to clipboard

Yisheng Xiao, Pei Guo, Zechen Sun, Juntao Li, Kai Song, Min Zhang

Make Imagination Clearer! Stable Diffusion-based Visual Imagination for Multimodal Machine Translation (2025.acl-long)

Challenge:	Iterative non-autoregressive (NAR) models have recently demonstrated impressive performance in varied generation tasks, surpassing the autoregressive Transformer.
Approach:	They propose a strategy to conduct efficient refinements without performance declines by using two simple metrics to identify potential problems existing in current refinement processes.
Outcome:	The proposed model outperforms the autoregressive Transformer by around one BLEU on average.

Copied to clipboard

Andong Chen, Yuchen Song, Kehai Chen, Xuefeng Bai, Muyun Yang, Liqiang Nie, Jie Liu, Tiejun Zhao, Min Zhang

MMEvol: Empowering Multimodal Large Language Models with Evol-Instruct (2025.findings-acl)

Challenge:	Experimental results show that our model significantly outperforms existing multimodal MT and text-only MT.
Approach:	They propose a stable diffusion-based imagination network into a multimodal large language model to generate an image for each source sentence.
Outcome:	The proposed model outperforms existing multimodal and text-only MT and achieves an average improvement of 14 BLEU points on Multi30K and MSCOCO multimodal MT benchmarks.

Copied to clipboard

Run Luo, Haonan Zhang, Longze Chen, Ting-En Lin, Xiong Liu, Yuchuan Wu, Min Yang, Yongbin Li, Minzheng Wang, Pengpeng Zeng, Lianli Gao, Heng Tao Shen, Yunshui Li, Hamid Alinejad-Rokny, Xiaobo Xia, Jingkuan Song, Fei Huang

DimA: A Parameter-efficient Fine-tuning Method with Knowledge Transfer Based on Transformer (2024.lrec-main)

Challenge:	a new framework for image-text instruction data evolution improves MLLM performance . lack of high-quality instruction data remains a major bottleneck in ML modeling .
Approach:	They propose a multimodal instruction data evolution framework that iteratively enhances data quality through fine-grained perception, cognitive reasoning, and interaction evolution.
Outcome:	The proposed approach improves MLLM performance in nine vision-language tasks while using significantly less data.

Copied to clipboard

Wenxuan Zhang, Min Huang, Zhuoyang Song, Qinghai Miao

Crossing the Reward Bridge: Expanding Reinforcement Learning with Verifiable Rewards Across Diverse Domains (2026.acl-long)

Challenge:	Pre-trained language models (PLMs) have demonstrated impressive performance across various downstream tasks, but fine-tuning is computationally expensive and storage-intensive.
Approach:	They propose a parameter-efficient method called DimA which enhances the transformer architecture by increasing the dimensionality.
Outcome:	The proposed method achieves state-of-the-art results in GLUE and XSUM tasks while utilizing less than 1% of the original model’s parameters.

Copied to clipboard

Yi Su, Dian Yu, Linfeng Song, Juntao Li, Haitao Mi, Zhaopeng Tu, Min Zhang, Dong Yu

Challenge:	Reinforcement learning with verifiable rewards (RLVR) has been effective on structured tasks, but its reliance on simple, rule-based verifiers creates a bottleneck.
Approach:	They propose a framework that uses a generative verifier to provide soft, probabilistic rewards.
Outcome:	The proposed framework outperforms existing models up to 10x their size and can be scalable and effective.

SrDetection: A Self-Referential Framework for Data Leakage Detection in Code Large Language Models (2026.findings-acl)

Copied to clipboard

Shuaimin Li, Liyang Fan, Zeyang li, Zhuoyue Wan, Yufang Lin, Shiwen Ni, Feiteng Fang, Hamid Alinejad-Rokny, Yuanfeng Song, Kun Jing, Chen Jason Zhang, Min Yang

Hallucinations as Orthogonal Noise: Inference-Time Manifold Alignment via Dynamic Contextual Orthogonalization (2026.findings-acl)

Challenge:	Existing methods for evaluating code large language models assume access to proprietary training corpora or use external reference sets with manually tuned, non-generalizable thresholds.
Approach:	They propose a framework for self-referential leakage detection for gray-box and black-box settings.
Outcome:	The proposed framework improves average F1 by 21.52 points in the gray-box setting and 14.46 points in black-box settings over strong baselines.

Copied to clipboard

Mingkuan Zhao, Wentao Hu, Tianchen Huang, Yuheng Min, Suquan Chen, Yide Gao, Yanbo Zhai, Shuangyong Song, Xuelong Li

Reasoning

Challenge:	Hallucinations in Large Language Models persist in critical domains where generated content diverges from contextual facts or logical constraints.
Approach:	They propose to generate hallucinations as orthogonal noise relative to the semantic manifold of the residual stream.
Outcome:	The proposed method achieves superior contextual faithfulness compared to state-of-the-art methods.

Covariance Matrix-Driven Image Channel Allocation for Multimodal Fake News Detection (2026.findings-acl)

Copied to clipboard

Zongliang Han, Wenyu Guo, Guoqing Jin, Yang Liu, Yan Song, Dong Yu, Wang Min

BrainECHO: Semantic Brain Signal Decoding through Vector-Quantized Spectrogram Reconstruction for Whisper-Enhanced Text Generation (2025.findings-acl)

Challenge:	Existing methods focus on designing efficient multimodal fusion frameworks to bridge the semantic gap between images and texts.
Approach:	They propose a covariance matrix-driven image channel allocation method that expands the number of original channel maps and assigns importance scores to the expanded channel maps.
Outcome:	The proposed method achieves state-of-the-art on three public multimodal fake news detection benchmark datasets.

Copied to clipboard

Jilong Li, Zhenxi Song, Jiaqi Wang, Meishan Zhang, Honghai Liu, Min Zhang, Zhiguo Zhang

Evaluating Research Novelty Detection: Counterfactual Approaches (D19-53)

Challenge:	Current EEG/MEG-to-text decoding systems rely on teacher-forcing methods . pre-trained large language models are over-dominant in decoding text from brain activity .
Approach:	They propose a framework that employs decoupled representation learning to achieve state-of-the-art performance on EEG and MEG datasets.
Outcome:	The proposed framework achieves state-of-the-art performance on EEG and MEG datasets.

Copied to clipboard

Reinald Kim Amplayo, Seung-won Hwang, Min Song

Challenge:	Despite its importance, this direction of research has not been explored as much.
Approach:	They propose to use counterfactual simulations to evaluate paper novelty detection models . they ask models to differentiate papers at time t and counterf actual paper from future time .
Outcome:	The proposed models can be compared against a set of papers with a given date and with different annotations.

Towards a Holistic and Automated Evaluation Framework for Multi-Level Comprehension of LLMs in Book-Length Contexts (2025.emnlp-main)

Copied to clipboard

Yuho Lee, Jiaqi Deng, Nicole Hee-Yeon Kim, Hyangsuk Min, Taewon Yun, Minjeong Ban, Kim Yul, Hwanjun Song

Challenge:	HAMLET is a framework for evaluating the long-context comprehension of large language models.
Approach:	They propose a framework for evaluating the long-context comprehension of large language models . HAMLET structures key information of source texts into a three-level hierarchy .
Outcome:	HAMLET achieves 90% agreement with expert judgments while reducing evaluation cost by up to 25.

Def-DTS: Deductive Reasoning for Open-domain Dialogue Topic Segmentation (2025.findings-acl)

Copied to clipboard

Seungmin Lee, Yongsang Yoo, Minhwa Jung, Min Song

Natural Language Interfaces

Challenge:	Dialogue Topic Segmentation (DTS) suffers from data shortage, labeling ambiguity, and incremental complexity of recently proposed solutions.
Approach:	They propose a method that employs a structured prompting approach for context summarization, utterance intent classification, and deductive topic shift detection.
Outcome:	The proposed method outperforms traditional and state-of-the-art approaches in various dialogue settings.

JOLT-SQL: Joint Loss Tuning of Text-to-SQL with Confusion-aware Noisy Schema Sampling (2025.emnlp-main)

Copied to clipboard

Jinwang Song, Hongying Zan, Kunli Zhang, Lingling Mu, Yingjie Han, Haobo Hua, Min Peng

Programming Languages in NLP

Challenge:	Recent advances in Large Language Models have improved Text-to-SQL methods . however, they still face challenges such as complex multi-stage pipelines and poor robustness to noisy schema information.
Approach:	They propose a single-stage SFT framework that optimizes schema linking and SQL generation via a unified loss.
Outcome:	Experiments on the Spider and BIRD benchmarks show that JOLT-SQL achieves state-of-the-art execution accuracy among comparable-size open-source models.

D-QRELO: Training- and Data-Free Delta Compression for Large Language Models via Quantization and Residual Low-Rank Approximation (2026.findings-acl)

Copied to clipboard

Junlin Li, Shuangyong Song, Guodong DU, Ngai Wong, Xuebo Liu, Yongxiang Li, Min Zhang, Jing Li, Xuelong Li

sudo rm -rf agentic_security (2025.acl-industry)

Challenge:	Existing methods for fine-tuned large language models fail on fine-scale datasets . large data scale amplifies delta parameter magnitude, singular values, and entropy, causing compression errors.
Approach:	They propose a training- and data-free delta compression method that captures dominant delta structure and compensates residual low-rank approximation to recover fine-grained details from smaller residual error.
Outcome:	The proposed method outperforms existing methods on large-scale datasets on dense and MoE architectures.

Copied to clipboard

Sejin Lee, Jian Kim, Haon Park, Ashkan Yousefpour, Sangyoon Yu, Min Song

Responsible & Trustworthy NLP

Challenge:	Large Language Models (LLMs) are increasingly used as computer-use agents . authors present a novel attack framework that bypasses refusal-trained safeguards .
Approach:	They propose a new attack framework that bypasses refusal-trained safeguards in LLMs . SUDO iteratively refines its attacks based on a built-in refusal feedback . authors highlight need for robust, context-aware safeguards if LLM is to be used .
Outcome:	The proposed framework bypasses refusal-trained safeguards in commercial agents . it achieves a stark attack success rate of 24.41% (with no refinement) and up to 41.33% (by iterative refinement).

PiKGL: Leveraging Pruned Knowledge Graphs for Explainable Stance Detection (2026.tacl-1)

Copied to clipboard

Bingbing Wang, Jingjie Lin, Zhixin Bai, Xintong Song, Qianlong Wang, Min Yang, Xi Zeng, Jing Li, Ruifeng Xu

Sentiment Analysis

Challenge:	Experimental results demonstrate that a Pruned interpretable knowledge Graph Learning framework for explainable stance detection is state-of-the-art for social media stance prediction.
Approach:	They propose a Pruned interpretable knowledge Graph Learning framework for explainable stance detection that incorporates commonsense knowledge and prunes redundant information to ensure precision and minimize noise.
Outcome:	The proposed framework achieves state-of-the-art on three public datasets.

MoDification: Mixture of Depths Made Easy (2025.naacl-long)

Copied to clipboard

Chen Zhang, Meizhi Zhong, Qimeng Wang, Xuantao Lu, Zheyu Ye, Chengqiang Lu, Yan Gao, Yao Hu, Kehai Chen, Min Zhang, Dawei Song

Green & Sustainable NLP

Challenge:	Long-context efficiency is a trending topic in large language model (LLM) serving.
Approach:	They propose a method to combine long-context efficiency and mixture of depths to bring down both latency and memory.
Outcome:	The proposed method achieves 1.2 speedup in latency and 1.8 reduction in memory compared to original LLMs especially in long-context applications.

Smart-Searcher: Incentivizing the Dynamic Knowledge Acquisition of LLMs via Reinforcement Learning (2025.findings-emnlp)

Copied to clipboard

Huatong Song, Jinhao Jiang, Wenqing Tian, Zhipeng Chen, Yuhuan Wu, Jiahao Zhao, Yingqian Min, Xin Zhao, Lei Fang, Ji-Rong Wen

Responsible & Trustworthy NLP

Challenge:	Large Language Models (LLMs) are powerful but prone to hallucinations due to static knowledge. Retrieval-augmented generation (RAG) helps by injecting external information, but current methods are costly, generalize poorly, or ignore the model’s internal knowledge.
Approach:	They propose a framework to train large language models to leverage both internal and external knowledge sources.
Outcome:	The proposed framework outperforms existing methods and achieves efficient retrieval-augmented reasoning.

Reading Like HER: Human Reading Inspired Extractive Summarization (D19-1)

Copied to clipboard

Ling Luo, Xiang Ao, Yan Song, Feiyang Pan, Min Yang, Qing He

Information Extraction & Text Mining

Challenge:	Existing methods for extracting text summarization are abstractive and extractive.
Approach:	They propose a novel approach for extractive summarization by simulating two stages . they adopt a convolutional neural network to encode gist of paragraphs for rough reading .
Outcome:	The proposed method significantly outperforms the state-of-the-art extractive methods on CNN and DailyMail datasets.

Towards Effective and Efficient Continual Pre-training of Large Language Models (2025.acl-long)

Copied to clipboard

Jie Chen, Zhipeng Chen, Jiapeng Wang, Kun Zhou, Yutao Zhu, Jinhao Jiang, Yingqian Min, Xin Zhao, Zhicheng Dou, Jiaxin Mao, Yankai Lin, Ruihua Song, Jun Xu, Xu Chen, Rui Yan, Zhewei Wei, Di Hu, Wenbing Huang, Ji-Rong Wen

Multi-Turn Dialogue Generation in E-Commerce Platform with the Context of Historical Dialogue (2020.findings-emnlp)

Challenge:	Continual pre-training (CPT) has been an important approach for adapting language models to specific domains or tasks.
Approach:	They propose a Continual pre-training method that can greatly improve Chinese language ability and scientific reasoning ability of LLMs.
Outcome:	The proposed method can greatly improve Chinese language ability and scientific reasoning ability of LLMs.

Copied to clipboard

WeiSheng Zhang, Kaisong Song, Yangyang Kang, Zhongqing Wang, Changlong Sun, Xiaozhong Liu, Shoushan Li, Min Zhang, Luo Si

Dialogue Systems & Conversational Agents

Challenge:	Existing research on customer service dialogue generation generates generic responses from sellers . however, such cost prohibits small businesses, and multiturn dialogue generation is becoming more popular.
Approach:	They propose a novel and extensible dialogue generation method by leveraging sellers’ historical dialogue information to generate generic seller responses.
Outcome:	The proposed model can generate high-quality responses that cater to specific sellers’ characteristics and exhibit consistent superiority over baselines on a real-world multi-turn customer service dialogue dataset.

Retrieval Visual Contrastive Decoding to Mitigate Object Hallucinations in Large Vision-Language Models (2025.findings-acl)

Copied to clipboard

Jihoon Lee, Min Song

Evaluating Prompting Strategies for Grammatical Error Correction Based on Language Proficiency (2024.lrec-main)

Challenge:	Large Vision Language Models are not free from the issue of Object Hallucination (OH) OH is a phenomenon where LVLMs generate hallucinated objects and descriptions in their outputs.
Approach:	They propose a method to suppress OH by referencing images from AI-generated images at the logit level.
Outcome:	The proposed method significantly improves existing methods on visual contrast decoding.

Copied to clipboard

Min Zeng, Jiexin Kuang, Mengyang Qiu, Jayoung Song, Jungyeul Park

Low-Resource NLP

Challenge:	generative LLMs have been known for overcorrection where results obtain higher recall measures than precision measures.
Approach:	They propose to use generative LLMs to prompt grammatical error correction using a model based on language proficiency to examine the interaction between LLM's performance and L2 language proficiency.
Outcome:	The proposed model improves on zero-shot and few-shot prompting and fine-tuning models for grammatical error correction for learners of English as a foreign language based on the different proficiency levels.

TelME: Teacher-leading Multimodal Fusion Network for Emotion Recognition in Conversation (2024.naacl-long)

Copied to clipboard

Taeyang Yun, Hyunkuk Lim, Jeonghwan Lee, Min Song

Sentiment Analysis

Challenge:	Emotion Recognition in Conversation (ERC) aims to identify emotions expressed by participants at each turn within a conversation.
Approach:	They propose a Teacher-leading Multimodal fusion network for ERC that integrates cross-modal knowledge distillation to transfer information from a lan- guage model acting as the teacher to non- verbal students.
Outcome:	The proposed model achieves state-of-the-art in a multi-speaker conversation dataset for ERC.

AQuilt: Weaving Logic and Self-Inspection into Low-Cost, High-Relevance Data Synthesis for Specialist LLMs (2025.emnlp-main)

Copied to clipboard

Xiaopeng Ke, Hexuan Deng, Xuebo Liu, Jun Rao, Zhenxi Song, Jun Yu, Min Zhang

Responsible & Trustworthy NLP

Challenge:	Existing approaches to synthesis large language models often suffer from performance limitations and high computational costs.
Approach:	They propose a framework for constructing instruction-tuning data from unlabeled data for any specialized domains from corresponding unlabed data.
Outcome:	The proposed framework is comparable to DeepSeek-V3 while utilizing just 17% of the production cost.

CaDRL: Document-level Relation Extraction via Context-aware Differentiable Rule Learning (2025.coling-main)

Copied to clipboard

Kunli Zhang, Pengcheng Wu, Bohan Yu, Kejun Wu, Aoze Zheng, Xiyang Huang, Chenkang Zhu, Min Peng, Hongying Zan, Yu Song

Information Extraction & Text Mining

Challenge:	Existing methods for document-level relation extraction (DocRE) lack logic and transparency.
Approach:	They propose a Context-aware differentiable rule learning framework that learns the doc-specific logical rule to avoid suboptimal constraints.
Outcome:	The proposed framework outperforms existing rule-based frameworks on three DocRE datasets.

Towards Multi-dimensional Evaluation of LLM Summarization across Domains and Languages (2025.acl-long)

Copied to clipboard

Hyangsuk Min, Yuho Lee, Minjeong Ban, Jiaqi Deng, Nicole Hee-Yeon Kim, Taewon Yun, Hang Su, Jason Cai, Hwanjun Song

Summarization

Challenge:	Existing evaluation frameworks for text summarization lack domain-specific assessment criteria and are predominantly English-centric.
Approach:	They propose a multi-dimensional, multi-domain evaluation of summarization in English and Chinese that incorporates specialized assessment criteria for each domain and leverages a debate system to enhance annotation quality.
Outcome:	The proposed evaluation framework provides a multi-dimensional, multi-domain evaluation of summarization in English and Chinese.

Code-Switching for Enhancing NMT with Pre-Specified Translation (N19-1)

Copied to clipboard

Kai Song, Yue Zhang, Heng Yu, Weihua Luo, Kun Wang, Min Zhang

Multilinguality

Challenge:	Existing methods to constrain NMT use placeholder tags for lexicon words and hard constraints during decoding.
Approach:	They propose to use placeholder tags to replace lexicon words with target translations . they use a data augmentation method to make code-switched training data .
Outcome:	The proposed method improves translation quality without hurting unconstrained words.

Enhancing EEG-to-Text Decoding through Transferable Representations from Pre-trained Contrastive EEG-Text Masked Autoencoder (2024.acl-long)

Copied to clipboard

Jiaqi Wang, Zhenxi Song, Zhengyu Ma, Xipeng Qiu, Min Zhang, Zhiguo Zhang