Papers by Peng Jin

Tracking Life’s Ups and Downs: Mining Life Events from Social Media Posts for Mental Health Analysis (2025.acl-long)

Challenge:	Previous work shows that large language models generate hallucinations, yet the origins and mechanisms of these signals remain unclear.
Approach:	They propose to validate and disentangle two different pathways for truthfulness cues . they also propose to use the same mechanism to derive self-contained evidence from the generated answer .
Outcome:	The proposed applications improve hallucination detection performance by integrating two different inputs.

Copied to clipboard

Minghao Lv, Siyuan Chen, Haoan Jin, Minghao Yuan, Qianqian Ju, Yujia Peng, Kenny Q. Zhu, Mengyue Wu

End-to-End Modeling via Information Tree for One-Shot Natural Language Spatial Video Grounding (2022.acl-long)

Challenge:	Existing studies have indicated that major life events can greatly impact individuals’ mental health, but shedding its light on social media data is challenging due to the complexity and ambiguity nature of life events.
Approach:	They propose to extract life events mentioned in posts on social media to uncover a social media event dataset which includes 12 major life event categories that are likely to occur in everyday life.
Outcome:	The proposed dataset includes 12 life event categories that are likely to occur in everyday life and is human-annotated under iterative procedure and boasts a high level of quality.

Copied to clipboard

Mengze Li, Tianbao Wang, Haoyu Zhang, Shengyu Zhang, Zhou Zhao, Jiaxu Miao, Wenqiao Zhang, Wenming Tan, Jin Wang, Peng Wang, Shiliang Pu, Fei Wu

Self-Consistency Boosts Calibration for Math Reasoning (2024.findings-emnlp)

Challenge:	Existing methods for grounding video frames with dense annotations require enormous amount of human effort.
Approach:	They propose to ground natural language in video frames with only one frame labeled . they propose an end-to-end model that eliminates interference of irrelevant frames .
Outcome:	The proposed model can ground natural language in all video frames with only one frame labeled . the proposed model eliminates interference of irrelevant frames based on branch search and cropping techniques .

Copied to clipboard

Ante Wang, Linfeng Song, Ye Tian, Baolin Peng, Lifeng Jin, Haitao Mi, Jinsong Su, Dong Yu

Generating Structured Pseudo Labels for Noise-resistant Zero-shot Video Sentence Localization (2023.acl-long)

Challenge:	Existing solutions for math reasoning tasks use semantic parsing or AST decoding, but performance can degrade dramatically even with slight changes to the questions.
Approach:	They propose three calibration methods based on self-consistency for math reasoning tasks.
Outcome:	The proposed methods bridge model confidence and accuracy better than existing methods based on p(True) or logit.

Copied to clipboard

Minghang Zheng, Shaogang Gong, Hailin Jin, Yuxin Peng, Yang Liu

COPEN: Probing Conceptual Knowledge in Pre-trained Language Models (2022.emnlp-main)

Challenge:	Existing zero-shot pipelines generate event proposals and then generate a pseudo query for each event proposal.
Approach:	They propose a Structure-based Pseudo Label generation (SPL) that generates free-form interpretable pseudo queries before constructing query-dependent event proposals.
Outcome:	The proposed method learns with only video data without any annotation . it generates free-form interpretable pseudo queries before constructing query-dependent event proposals .

Copied to clipboard

Hao Peng, Xiaozhi Wang, Shengding Hu, Hailong Jin, Lei Hou, Juanzi Li, Zhiyuan Liu, Qun Liu

Self-Alignment for Factuality: Mitigating Hallucinations in LLMs via Self-Evaluation (2024.acl-long)

Challenge:	Existing knowledge probing studies focus on evaluating factual knowledge of pre-trained language models (PLMs) but ignore conceptual knowledge.
Approach:	They evaluate conceptual knowledge of pre-trained language models by annotating 24k data instances covering 393 concepts.
Outcome:	The proposed tasks evaluate pre-trained language models' conceptual knowledge of entities, learn conceptual properties, and conceptualize entities in contexts.

Copied to clipboard

Xiaoying Zhang, Baolin Peng, Ye Tian, Jingyan Zhou, Lifeng Jin, Linfeng Song, Haitao Mi, Helen Meng

TongGu: Mastering Classical Chinese Understanding with Knowledge-Grounded Large Language Models (2024.findings-emnlp)

Challenge:	Existing approaches to addressing factual inaccuracies require high-quality human factuality annotations to mitigate these hallucinations.
Approach:	They propose to leverage the self-evaluation capability of an LLM to provide training signals that steer the model towards factuality.
Outcome:	The proposed approach significantly improves factual accuracy over LLMs across three key knowledge-intensive tasks on TruthfulQA and BioGEN.

Copied to clipboard

Jiahuan Cao, Dezhi Peng, Peirong Zhang, Yongxin Shi, Yang Liu, Kai Ding, Lianwen Jin

PCEE-BERT: Accelerating BERT Inference via Patient and Confident Early Exiting (2022.findings-naacl)

Challenge:	Large Language Models (LLMs) have demonstrated remarkable capability in Natural Language Processing (NLP), but struggle with Classical Chinese Understanding (CCU) Existing models, including general-purpose and preliminary LLMs, lack the ability to address CCU in data-demanding and knowledge-intensive tasks.
Approach:	They propose to use a classical Chinese corpora-based instruction-tuning dataset to unlock the full CCU potential of LLMs.
Outcome:	The proposed model unlocks the full CCU potential of LLMs by preserving its foundational knowledge while maintaining redundancy-aware tuning (RAT) and CCU-RAG.

Copied to clipboard

Zhen Zhang, Wei Zhu, Jinfan Zhang, Peng Wang, Rize Jin, Tae-Sun Chung

Cross-lingual Text-to-SQL Semantic Parsing with Representation Mixup (2022.findings-emnlp)

Challenge:	Pre-trained language models (PLMs) are the state-of-the-art (SOTA) models for natural language processing (NLP).
Approach:	They propose a patient and confident early exiting BERT (PCEE-BERT) that can work with different PLMs and popular model compression methods.
Outcome:	The proposed method outperforms existing models on the GLUE benchmarks and achieves different speed-up ratios.

Copied to clipboard

Peng Shi, Linfeng Song, Lifeng Jin, Haitao Mi, He Bai, Jimmy Lin, Dong Yu

Multilinguality

Challenge:	Experimental results show that Rex can benefit from cross-lingual training and improve the effectiveness of semantic parsers.
Approach:	They propose a Representation Mixup Framework for effectively exploiting translations in the cross-lingual Text-to-SQL task.
Outcome:	The proposed framework can benefit from cross-lingual training and improve the effectiveness of semantic parsers, achieving state-of-the-art performance.

HiSMatch: Historical Structure Matching based Temporal Knowledge Graph Reasoning (2022.findings-emnlp)

Copied to clipboard

Zixuan Li, Zhongni Hou, Saiping Guan, Xiaolong Jin, Weihua Peng, Long Bai, Yajuan Lyu, Wei Li, Jiafeng Guo, Xueqi Cheng

SYNTHIA: Novel Concept Design with Affordance Composition (2025.acl-long)

Challenge:	Temporal Knowledge Graphs (TKGs) store facts as triples in the form of subject, relation, object, timestamps.
Approach:	They propose a Temporal Knowledge Graph (TKG) model that extends each triple with a timestamp to describe dynamic facts.
Outcome:	The proposed model improves on six benchmark datasets with up to 5.6% performance improvement compared to the state-of-the-art models.

Copied to clipboard

Hyeonjeong Ha, Xiaomeng Jin, Jeonghwan Kim, Jiateng Liu, Zhenhailong Wang, Khanh Duy Nguyen, Ansel Blume, Nanyun Peng, Kai-Wei Chang, Heng Ji

Video-LLaVA: Learning United Visual Representation by Alignment Before Projection (2024.emnlp-main)

Challenge:	Existing studies on concept design using text-to-image models have enabled rapid ideation of novel visual concepts.
Approach:	They propose a framework for generating novel, functionally coherent designs based on desired affordances by decomposing concepts into parts and affordance . they also develop a curriculum learning scheme that fine-tunes T2I models to progressively learn affordance composition while maintaining visual novelty.
Outcome:	The proposed framework outperforms state-of-the-art models for novelty and functional coherence in human evaluation.

Copied to clipboard

Bin Lin, Yang Ye, Bin Zhu, Jiaxi Cui, Munan Ning, Peng Jin, Li Yuan

Entropy Guided Extrapolative Decoding to Improve Factuality in Large Language Models (2025.coling-main)

Challenge:	Existing approaches to visual-language understanding lack unified tokenization for images and videos . lack of unified visual representations makes it difficult to learn multi-modal interactions from poor projection layers.
Approach:	They propose to unify visual representation into the language feature space to advance the foundational LLM towards a unified LVLM.
Outcome:	The proposed model outperforms Video-ChatGPT on image benchmarks and on 9 image benchmark benchmarks.

Copied to clipboard

Souvik Das, Lifeng Jin, Linfeng Song, Haitao Mi, Baolin Peng, Dong Yu

Reasoning over Precedents Alongside Statutes: Case-Augmented Deliberative Alignment for LLM Safety (2026.acl-long)

Challenge:	Large language models (LLMs) exhibit impressive natural language capabilities but suffer from hallucination – generating content that does not align with realworld facts.
Approach:	They propose to extrapolate critical token probabilities beyond the last layer to improve decoding by manipulating the predicted distributions at inference time.
Outcome:	The proposed methods surpass state-of-the-art on multiple datasets by large margins.

Copied to clipboard

Can Jin, Rui Wu, Tong Che, Qixin Zhang, Hongwu Peng, Jiahui Zhao, Zhenting Wang, Wenqi Wei, Ligong Han, Zhao Zhang, Yuan Cao, Ruixiang Tang, Dimitris N. Metaxas

Robustness in NLP

Challenge:	OpenAI introduces deliberative alignment (DA) to enhance safety of its o-series models, but effectiveness of this approach in open-source LLMs is understudied.
Approach:	They propose a case-augmented deliberative alignment method for large language models . they propose to use reinforcement learning on self-generated safety reasoning chains .
Outcome:	The proposed method avoids narrowly enumerated rules and allows broader adaptability.

LogicPro: Improving Complex Logical Reasoning via Program-Guided Learning (2025.acl-long)

Copied to clipboard

Jin Jiang, Yuchen Yan, Yang Liu, Jianing Wang, Shuai Peng, Xunliang Cai, Yixin Cao, Mengdi Zhang, Liangcai Gao

ReFT: Reasoning with Reinforced Fine-Tuning (2024.acl-long)

Challenge:	LogicPro is a data synthesis method that uses LeetCode-style algorithm problems and their corresponding Program solutions to generate complex logic data.
Approach:	They propose a new method which leverages LeetCode-style algorithm Problems and their corresponding Program solutions to synthesize complex logic data in text format.
Outcome:	The proposed method outperforms existing models for BBH27, LogicBench, DROP, AR-LSAT, and GSM8K, and a wide range of reasoning datasets.

Copied to clipboard

Luong Trung, Xinbo Zhang, Zhanming Jie, Peng Sun, Xiaoran Jin, Hang Li

Praetor: A Fine-Grained Generative LLM Evaluator with Instance-Level Customizable Evaluation Criteria (2025.acl-long)

Challenge:	Existing approaches to improve the generalization of large language models are using Supervised Fine-Tuning (SFT) this approach does not show sufficient generalization ability because it only relies on the given CoT data.
Approach:	They propose to use Chain-of-Thought annotations to train Large Language Models using supervised fine-tuning to improve generalization.
Outcome:	The proposed approach outperforms SFT on GSM8K, MathQA, and SVAMP datasets and shows a superior generalization ability.

Copied to clipboard

Yongqi Leng, Renren Jin, Yue Chen, Zhuowen Han, Ling Shi, Jianxiang Peng, Lei Yang, Juesi Xiao, Deyi Xiong

Challenge:	Existing evaluation methods are inadequate to evaluate large language models (LLMs).
Approach:	They propose a fine-grained generative LLM evaluator with instance-level customazable evaluation criteria that can be used to evaluate large language models.
Outcome:	The proposed model outperforms existing LLM evaluators and instruction-tuned LLMs on multiple benchmarks and sets new SOTA results.

From Curated Data to Scalable Models: Continual Pre-training of Dense and MoE Large Language Models for Tibetan (2026.acl-long)

Copied to clipboard

Lei Yang, Leiyu Pan, Bojian Xiong, Renren Jin, Shaowei Zhang, Yue Chen, Ling Shi, Jiang Zhou, Junru Wu, Zhen Wang, Jianxiang Peng, Juesi Xiao, Tianyu Dong, Zhuowen Han, Zhuo Chen, Yuqi Ren, Deyi Xiong

Improving LLM Generations via Fine-Grained Self-Endorsement (2024.findings-acl)

Challenge:	Large language models have achieved remarkable success across a wide range of tasks, yet their performance remains heavily biased toward high-resource languages.
Approach:	They propose a pipeline for advancing Tibetan language modeling through multilingual continual pre-training with Tibetan, Chinese, and English.
Outcome:	The proposed model outperforms open-source and Tibetan-focused models on diverse tasks.

Copied to clipboard

Ante Wang, Linfeng Song, Baolin Peng, Lifeng Jin, Ye Tian, Haitao Mi, Jinsong Su, Dong Yu

Wrong-of-Thought: An Integrated Reasoning Framework with Multi-Perspective Verification and Wrong Information (2024.findings-emnlp)

Challenge:	Recent large language models (LLMs) have demonstrated remarkable capabilities but can still fail frequently on knowledge-intensive tasks.
Approach:	They propose a self-endorsement framework that leverages fine-grained fact-level comparisons across multiple sampled responses.
Outcome:	The proposed framework can improve factuality of generations with simple prompts across scales of LLMs.

Copied to clipboard

Yongheng Zhang, Qiguang Chen, Jingxuan Zhou, Peng Wang, Jiasheng Si, Jin Wang, Wenpeng Lu, Libo Qin

GBT: Generative Boosting Training Approach for Paraphrase Identification (2023.findings-emnlp)

Challenge:	Chain-of-Thought (CoT) is a key technique for enhancing the performance of Large Language Models.
Approach:	They propose a framework that optimizes outputs by utilizing wrong information and multi-perspective verification.
Outcome:	The proposed framework surpasses all baselines on 8 datasets and 5 LLMs.

Copied to clipboard

Rui Peng, Zhiling Jin, Yu Hong

Text Generation

Challenge:	Paraphrase Identification (PI) is a fundamental natural language understanding task with non-trivial challenges.
Approach:	They propose a Generative Boosting Training approach for Paraphrase Identification (PI) they use a seq2seq model to perform DA on misclassified instances periodically .
Outcome:	The proposed method outperforms state-of-the-art PI models on English and Chinese PI tasks with good efficiency and effectiveness.

ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization (2025.findings-emnlp)

Copied to clipboard

Zhensheng Jin, Xinze Li, Yifan Ji, Chunyi Peng, Zhenghao Liu, Qi Shi, Yukun Yan, Shuo Wang, Furong Peng, Ge Yu

RISER: Orchestrating Latent Reasoning Skills for Adaptive Activation Steering (2026.findings-acl)

Challenge:	Existing methods to train LLMs suffer from overthinking, leading to lengthy reasoning traces . Existing approaches to train large language models suffer from this problem .
Approach:	They propose a method to combine multiple reasoning chains for training LLMs . they use stepwise exploration and long-short switched sampling to evaluate reasoning paths .
Outcome:	The proposed method reduces reasoning lengths by approximately 30-50% . it also maintains or improves reasoning accuracy compared to baselines .

Copied to clipboard

Wencheng Ye, Xiaoyang Yuan, Yi Bin, Hengyu Jin, Liang Peng, Pengpeng Zeng, Heng Tao Shen

LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context Inference (2024.findings-emnlp)

Challenge:	Existing methods for domain-specific reasoning with large language models require updating parameter updates.
Approach:	They propose a plug-and-play intervention framework that adaptively steers LLM reasoning in activation space.
Outcome:	The proposed framework achieves zero-shot accuracy improvements of 3.4–6.5% over the base model while outperforming chain-of-thought-style reasoning with 2–3 higher token efficiency and robust accuracy gains.

Copied to clipboard

Zhongwei Wan, Ziang Wu, Che Liu, Jinfa Huang, Zhihong Zhu, Peng Jin, Longyue Wang, Li Yuan

Visual Data in NLP

Challenge:	Long-context Multimodal Large Language Models (MLLMs) require substantial computational resources for inference . the growth of their multimodal Key-Value (KV) cache challenges memory and time efficiency.
Approach:	They propose a fine-tuning-free approach that efficiently reduces the multimodal KV cache size while maintaining performance comparable to a full cache.
Outcome:	The proposed method reduces the multimodal KV cache size while maintaining performance comparable to a full cache.

Meeseeks: A Feedback-Driven, Iterative Self-Correction Benchmark evaluating LLMs’ Instruction Following Capability (2026.findings-acl)

Copied to clipboard

Jiaming Wang, Yunke Zhao, Peng Ding, Jun Kuang, Yibin Shen, Zhe Tang, Yilin Jin, ZongYu Wang, Xiaoyu Li, Xuezhi Cao

Mining the Cause of Political Decision-Making from Social Media: A Case Study of COVID-19 Policies across the US States (2021.findings-emnlp)

Challenge:	Existing models lack the ability to adhere to instructions, resulting in suboptimal performance.
Approach:	They propose an automated iterative instruction-following benchmark with integrated feedback mechanism.
Outcome:	The proposed benchmark identifies erroneous components in model responses and provides feedback accurately.

Copied to clipboard

Zhijing Jin, Zeyu Peng, Tejas Vaidhya, Bernhard Schoelkopf, Rada Mihalcea

Sentiment Analysis

Challenge:	Existing studies on political responsiveness focus on long-term policies collected over decades . recent COVID-19 pandemic has given rise to a new political phenomenon, where political leaders make frequent short-term decisions on the same controlled topic.
Approach:	They propose to use Twitter data to classify the sentiments toward governors of each state and conduct controlled studies and comparisons.
Outcome:	The proposed model focuses on the COVID-19 pandemic, where political leaders make frequent short-term decisions on the same controlled topic.

Contextual Modeling for Document-level ASR Error Correction (2024.lrec-main)

Copied to clipboard

Jin Jiang, Xunjian Yin, Xiaojun Wan, Wei Peng, Rongjun Li, Jingyuan Yang, Yanquan Zhou

SOP-Maze: Evaluating Large Language Models on Complicated Business Standard Operating Procedures (2026.findings-acl)

Challenge:	Existing work on document-level ASR error correction ignores contextual information . however, there are limited studies on incorporating contextual information into AEC .
Approach:	They propose a context-aware method that retrieves contextual information from a datastore . they use two English and two Chinese datasets to model document-level AEC .
Outcome:	The proposed model can utilize contextual information to improve document-level AEC . the data store containing contextual information provides even better results .

Copied to clipboard

Jiaming Wang, Zhe Tang, Zehao Jin, Hefei Chen, Yilin Jin, Peng Ding, Xiaoyu Li, Xuezhi Cao

Rethinking Positional Encoding in Tree Transformer for Code Representation (2022.emnlp-main)

Challenge:	Large language models (LLMs) are widely deployed as domain-specific agents, but evaluation of their capabilities in such contexts has not been fully explored.
Approach:	They propose a benchmark to evaluate LLMs' ability to follow instructions and make decisions in real-world scenarios.
Outcome:	The proposed benchmark is constructed from real-world business data and adapted into 23 complex SOP scenarios.

Copied to clipboard

Han Peng, Ge Li, Yunfei Zhao, Zhi Jin

Parrot: A Training Pipeline Enhances Both Program CoT and Natural Language CoT for Reasoning (2025.emnlp-main)

Challenge:	Recent works have proposed novel tree Transformers to capture the syntactic structure in source code.
Approach:	They propose a novel tree Transformer encoding node positions based on a description method for tree structures to incorporate inductive bias into Transformer.
Outcome:	The proposed model outperforms baselines on code summarization and completion tasks across two languages, and it is able to perform better on both local and global paradigms.

Copied to clipboard

Senjie Jin, Lu Chen, Zhiheng Xi, Yuhui Wang, Sirui Song, Yuhao Zhou, Xinbo Zhang, Peng Sun, Hong Lu, Tao Gui, Qi Zhang, Xuanjing Huang

Reusing Transferable Weight Increments for Low-resource Style Generation (2024.emnlp-main)

Challenge:	Existing work focuses on enabling models to generate natural language chain-of-thought rationales or leverage executable and verifiable code, such as Python.
Approach:	They propose a novel training pipeline that integrates sequential P-CoT and N-Co T generation and a subtask hybrid training strategy to facilitate natural language transferability.
Outcome:	The proposed training pipeline improves both N-CoT and P-Co T performance over the RL baseline.

Copied to clipboard

Chunzhen Jin, Eliot Huang, Heng Chang, Yaqi Wang, Peng Cao, Osmar Zaiane

Low-Resource NLP

Challenge:	Text style transfer (TST) is crucial in natural language processing, aiming to endow text with a new style without altering its meaning.
Approach:	They propose a framework to use style features in weight increments to transfer low-resource styles effectively.
Outcome:	The proposed framework achieves remarkable performance across different backbones, achieving particularly effective results in low-resource scenarios.

Multimodal Transformers are Hierarchical Modal-wise Heterogeneous Graphs (2025.acl-long)

Copied to clipboard

Yijie Jin, Junjie Peng, Xuanchao Lin, Haochen Yuan, Lan Wang, Cangzhi Zheng

Unsupervised Morphological Paradigm Completion (2020.acl-main)

Challenge:	Multimodal Sentiment Analysis (MSA) is a rapidly developing field that integrates multimodal information to recognize sentiments.
Approach:	They propose a multimodal fusion model that integrates multimodal information to recognize sentiments using multimodal transformers.
Outcome:	The proposed model achieves significantly higher performance than MulTs and the existing model is robust.

Copied to clipboard

Huiming Jin, Liwei Cai, Yihui Peng, Chen Xia, Arya McCarthy, Katharina Kann

Automatic Bug Detection in LLM-Powered Text-Based Games Using LLMs (2024.findings-acl)

Challenge:	a task of generating morphological paradigms is a challenging unsupervised task for natural language processing systems . acuidados y acciones del idioma es a problem in linguistic annotators.
Approach:	They propose a task of unsupervised morphological paradigm completion using raw text and a lemma list.
Outcome:	The proposed system outperforms trivial baselines on 14 typologically diverse languages with ease and higher accuracy than minimally supervised systems.

Copied to clipboard

Claire Jin, Sudha Rao, Xiangyu Peng, Portia Botchway, Jessica Quaye, Chris Brockett, Bill Dolan

Towards Multi-Relational Multi-Hop Reasoning over Dense Temporal Knowledge Graphs (2024.findings-acl)

Challenge:	Advancements in large language models (LLMs) are revolutionizing interactive game design, but they may exhibit flaws such as hallucinations, forgetfulness, or misinterpretation of prompts.
Approach:	They propose a method for automatically identifying LLM bugs from player game logs . their method surpasses unstructured bug-catching methods and fills the gap .
Outcome:	The proposed method surpasses unstructured bug-catching methods and fills the gap in detection of logical and design flaws.

Copied to clipboard

Jian Liu, Zihe Liu, Xueqiang Lyu, Peng Jin, Jinan Xu

Structured Data in NLP

Challenge:	Temporal knowledge graph reasoning is a crucial task for answering time-dependent questions within a knowledge graph (KG).
Approach:	They propose a temporal KG reasoning benchmark with over 200k entities and 960k questions that facilitate complex, multi-relational and multi-hop reasoning.
Outcome:	The proposed model is able to conduct pattern-aware and time-sensitive reasoning across temporal KGs and is scalable to a wide range of data conditions.

VisKoP: Visual Knowledge oriented Programming for Interactive Knowledge Base Question Answering (2023.acl-demo)

Copied to clipboard

Zijun Yao, Yuanyong Chen, Xin Lv, Shulin Cao, Amy Xin, Jifan Yu, Hailong Jin, Jianjun Xu, Peng Zhang, Lei Hou, Juanzi Li

Entropy-Based Vocabulary Substitution for Incremental Learning in Multilingual Neural Machine Translation (2022.emnlp-main)

Challenge:	Existing knowledge base question answering systems that parse natural language questions into knowledge oriented program language (KoPL) .
Approach:	They propose a knowledge base question answering system that integrates human into the loop to edit and debug queries.
Outcome:	The proposed system can debug and edit knowledge base questions on a million-entity-level . it provides auto-completion for its knowledge base schema and user interaction can fix a large portion of wrong KoPL programs to acquire the correct answer.

Copied to clipboard

Kaiyu Huang, Peng Li, Jin Ma, Yang Liu

Multilinguality

Challenge:	Existing methods to update a multilingual model with new language pairs are expensive and time-consuming.
Approach:	They propose an entropy-based vocabulary substitution method that walks through new language pairs for incremental learning while remaining the size of the original vocabulary.
Outcome:	The proposed method achieves better performance and saves excess overhead in a multilingual machine translation task.

RedundancyLens: Revealing and Exploiting Visual Token Processing Redundancy for Efficient Decoder-Only MLLMs (2025.findings-acl)

Copied to clipboard

Hongliang Li, Jiaxin Zhang, Wenhui Liao, Dezhi Peng, Kai Ding, Lianwen Jin

Knowledge Transfer in Incremental Learning for Multilingual Neural Machine Translation (2023.acl-long)

Challenge:	Current decoder-only architectures achieve higher performance but lower efficiency . cross-attention-based architectures skip visual token computations .
Approach:	They propose a training-free framework for analyzing trained MLLMs to investigate redundancy . they propose 'probe-activated Dynamic FFN and Hollow Attention' algorithms for visual token reductions and a layer ranking algorithm for inference acceleration.
Outcome:	The proposed framework achieves comparable performance to or better than state-of-the-art methods while remaining compatible with them.

Copied to clipboard

Kaiyu Huang, Peng Li, Jin Ma, Ting Yao, Yang Liu

Multilinguality

Challenge:	Existing studies focus on overcoming catastrophic forgetting on original language pairs while lacking encouragement to learn new knowledge from incremental learning.
Approach:	They propose a knowledge transfer method that can adapt original MNMT models to diverse incremental language pairs by flexibly introducing knowledge from external models into original models, which encourages the models to learn new language pairs.
Outcome:	The proposed method outperforms baselines on multiple languages while maintaining performance on original language pairs.

RAP: Efficient Text-Video Retrieval with Sparse-and-Correlated Adapter (2024.findings-acl)

Copied to clipboard

Meng Cao, Haoran Tang, Jinfa Huang, Peng Jin, Can Zhang, Ruyang Liu, Long Chen, Xiaodan Liang, Li Yuan, Ge Li

Green & Sustainable NLP

Challenge:	Text-Video Retrieval (TVR) aims to align relevant video content with natural language queries.
Approach:	They propose to conduct efficient text-video Retrieval with a salient-and-correlated AdaPter . they propose a low-rank modulation module to refine per-image features from frozen CLIP backbone .
Outcome:	Experiments on four TVR datasets show that the proposed method performs better than other methods.

CORES: Code-Oriented Reasoning for Complex Text-to-SQL and Generalizable TableQA (2026.findings-acl)

Copied to clipboard

Meng Zhang, Ruochun Jin, Yuanxi Peng, Wenjing Yang, Haotian Wang, Liting Sun, Kun Hu, Silin Yang, Zhang Ke-di