Papers by Ji Wang

A Survey of LLM-based Agents in Medicine: How far are we from Baymax? (2025.findings-acl)

Challenge:	Current work on understanding assembly code is oriented towards generating function names, which involve numerous abbreviations that make them confusing.
Approach:	They propose a control flow graph and pseudo code guided binary code summarization framework to learn the comprehensive binary function execution behavior and logic semantics.
Outcome:	The proposed framework improves the efficiency of reverse engineering on 3 different binary optimization levels for 3 different computer architectures.

Copied to clipboard

Wenxuan Wang, Zizhan Ma, Zheng Wang, Chenghan Wu, Jiaming Ji, Wenting Chen, Xiang Li, Yixuan Yuan

CART: A Generative Cross-Modal Retrieval Framework With Coarse-To-Fine Semantic Modeling (2025.acl-long)

Challenge:	Large Language Models (LLMs) are transforming healthcare through their ability to understand and assist with medical tasks.
Approach:	They analyze system profiles, clinical planning, medical reasoning frameworks, and external capacity enhancement.
Outcome:	The findings highlight the future directions in medical reasoning, physical system integration, and training simulations.

Copied to clipboard

Minghui Fang, Shengpeng Ji, Jialong Zuo, Hai Huang, Yan Xia, Jieming Zhu, Xize Cheng, Xiaoda Yang, Wenrui Liu, Gang Wang, Zhenhua Dong, Zhou Zhao

Too Long, Do Re-weighting for Efficient LLM Reasoning Compression (2026.acl-long)

Challenge:	Cross-modal retrieval tasks are used to retrieve data from one modality or another based on a query from another modality.
Approach:	They propose a generative cross-modal retrieval framework based on coarse-to-fine semantic modeling . they propose combining K-Means and RQ-VAE to discretize multimodal data into token sequences that support autoregressive generation.
Outcome:	The proposed framework achieves excellent performance and efficiency in multimodal retrieval tasks.

Copied to clipboard

Zhong-Zhi Li, Xiao Liang, Zihao Tang, Lei Ji, Peijie Wang, Haotian Xu, Xing W, Haizhen Huang, Weiwei Deng, Yeyun Gong, Zhijiang Guo, Xiao Liu, Fei Yin, Cheng-Lin Liu

Model Composition for Multimodal Large Language Models (2024.acl-long)

Challenge:	Large Language Models (LLMs) have recently achieved remarkable progress on complex reasoning tasks by leveraging extended Chain-of-Thought (CoT) techniques.
Approach:	They propose a method that uses Extended Chain-of-Thought (EFT) to reduce the number of output tokens by nearly 40% while maintaining the accuracy of the reasoning.
Outcome:	The proposed method reduces the number of output tokens by nearly 40% while maintaining the accuracy of the reasoning.

Copied to clipboard

Chi Chen, Yiyang Du, Zheng Fang, Ziyue Wang, Fuwen Luo, Peng Li, Ming Yan, Ji Zhang, Fei Huang, Maosong Sun, Yang Liu

Dual-Axis Generative Reward Model Toward Semantic and Turn-taking Robustness in Interactive Spoken Dialogue Models (2026.acl-long)

Challenge:	Existing methods for creating versatile MLLMs rely on joint training with paired instruction data, which is resource-intensive and challenging to extend to new modalities.
Approach:	They propose a new paradigm for multimodal large language models by reusing modality encoders and merging LLM parameters.
Outcome:	The proposed model retains the modal understanding capabilities of each original model.

Copied to clipboard

Yifu Chen, Shengpeng Ji, Zhengqing Liu, Qian Chen, Wen Wang, Ziqing Wang, Yangzhuo Li, Tianle Liang, Zhou Zhao

RotateCT: Knowledge Graph Embedding by Rotation and Coordinate Transformation in Complex Space (2022.coling-1)

Challenge:	Reinforcement learning (RL) has improved text- and vision-language models, but its application in SDMs is hindered.
Approach:	They propose a dual-axis Generative Reward Model that provides semantic quality and interaction timing for SDMs.
Outcome:	The proposed model achieves state-of-the-art performance on interaction-quality assessment across a wide spectrum of datasets.

Copied to clipboard

Yao Dong, Lei Wang, Ji Xiang, Xiaobo Guo, Yuqiang Xie

Gaussian Process based Deep Dyna-Q approach for Dialogue Policy Learning (2021.findings-acl)

Challenge:	Existing knowledge graph embedding methods fail to model non-commutative composition patterns . Existing methods are limited to complex space, resulting in a large number of parameters.
Approach:	They propose a knowledge graph embedding method that transforms the coordinates of each entity and then represents each relation as a rotation from head entity to tail entity in complex space.
Outcome:	The proposed method outperforms state-of-the-art methods on link prediction and path query answering.

Copied to clipboard

Guanlin Wu, Wenqi Fang, Ji Wang, Jiang Cao, Weidong Bao, Yang Ping, Xiaomin Zhu, Zheng Wang

Lookahead Q-Cache: Achieving More Consistent KV Cache Eviction via Pseudo Query (2025.emnlp-main)

Challenge:	Reinforcement learning (RL) is the main dialogue policy learning method in recent years.
Approach:	They propose a Gaussian Process based Deep Dyna-Q approach to dialogue policy learning . they propose evaluating the quality of experiences generated by the world model using a discriminator .
Outcome:	The proposed approach improves the effectiveness and efficiency of dialogue policy learning by 20% with fewer human-machine interactions.

Copied to clipboard

Yixuan Wang, Shiyu Ji, Yijun Liu, Yuzhuang Xu, Yang Xu, Qingfu Zhu, Wanxiang Che

Challenge:	Existing KV cache eviction methods prune tokens using prefilling-stage attention scores, causing inconsistency with actual inference queries.
Approach:	They propose a lookahead q-cache framework that generates low-cost pseudo lookaheaded queries to better approximate the true decoding-stage queries.
Outcome:	The proposed framework outperforms existing methods on LongBench and Needle-in-a-Haystack benchmarks and can be flexibly combined to yield further improvements.

Learning to Solve Domain-Specific Calculation Problems with Knowledge-Intensive Programs Generator (2025.naacl-long)

Copied to clipboard

Chengyuan Liu, Shihang Wang, Lizhi Qing, Jun Lin, Ji Zhang, Fei Wu, Kun Kuang

Watermark under Fire: A Robustness Evaluation of LLM Watermarking (2025.findings-emnlp)

Challenge:	Domain Large Language Models (LLMs) are developed for domain-specific tasks based on general LLMs, but it still requires professional knowledge to facilitate the expertise for some domain- specific tasks.
Approach:	They propose a pipeline to solve domain-specific calculation problems with KIPG . they use it to extract key variables and calculate outcomes dependent on domain knowledge .
Outcome:	The proposed pipeline solves domain-specific calculation problems more effectively . it generates knowledge-intensive programs according to the domain- specific documents .

Copied to clipboard

Jiacheng Liang, Zian Wang, Spencer Hong, Shouling Ji, Ting Wang

WavRAG: Audio-Integrated Retrieval Augmented Generation for Spoken Dialogue Models (2025.acl-long)

Challenge:	Various watermarking methods have been proposed to identify LLM-generated texts . lack of unified evaluation platforms has left many critical questions unanswered .
Approach:	They systematize existing LLM watermarkers and watermark removal attacks and develop a unified platform that integrates them.
Outcome:	The proposed systematizes existing LLM watermarkers and watermark removal attacks, mapping out their design spaces.

Copied to clipboard

Yifu Chen, Shengpeng Ji, Haoxiao Wang, Ziqing Wang, Siyu Chen, Jinzheng He, Jin Xu, Zhou Zhao

AgentGym2: Benchmarking Large Language Model Agents in De-Idealized Real-World Environments (2026.acl-long)

Challenge:	Existing RAG frameworks rely on Automatic Speech Recognition to process speech input, which discards crucial audio information and increases computational overhead.
Approach:	They propose a retrieval augmented generation framework with native, end-to-end audio support that integrates audio and text into a unified knowledge representation.
Outcome:	The proposed framework can perform 10x faster than current pipelines while delivering 10x acceleration.

Copied to clipboard

Zhiheng Xi, Dingwen Yang, Jiaqi Liu, Jixuan Huang, Honglin Guo, Baodai Huang, Tinggang Chen, Qi Zhang, Zhonghang Lu, Chenyu Liu, Jiajun Sun, Jiazheng Zhang, Dingwei Zhu, Xin Guo, Junzhe Wang, Zhihao Zhang, Yuming Yang, Junjie Ye, Minghe Gao, Dongrui Liu, Jiaming Ji, Guohao Li, Tao Gui, Qi Zhang, Xuanjing Huang

Decoding by Contrasting Knowledge: Enhancing Large Language Model Confidence on Edited Facts (2025.acl-long)

Challenge:	Existing benchmarks evaluate agents in simplified, idealized settings, relying on pre-packaged tool interfaces, overlooking critical steps, and assume inputs are clean and fully specified.
Approach:	They propose a framework that evaluates language agents in simplified, idealized settings . they show that even SOTA systems like Gemini and GPT-5 struggle on AgentGym2 .
Outcome:	Experiments on 15 proprietary and open-source models show that even SOTA systems like Gemini and GPT-5 struggle on AgentGym2 .

Copied to clipboard

Baolong Bi, Shenghua Liu, Lingrui Mei, Yiwei Wang, Junfeng Fang, Pengliang Ji, Xueqi Cheng

Length Generalization of Causal Transformers without Position Encoding (2024.findings-acl)

Challenge:	In-context knowledge editing (ICE) is currently the most effective method for knowledge editing, but it is constrained by the black-box modeling of LLMs and lacks interpretability.
Approach:	They propose a method to decode new knowledge by comparing logits with unedited knowledge to improve the accuracy of LLMs.
Outcome:	The proposed method improves the performance of LLaMA3-8B-instruct on MQuAKE by up to 219%.

Copied to clipboard

Jie Wang, Tao Ji, Yuanbin Wu, Hang Yan, Tao Gui, Qi Zhang, Xuanjing Huang, Xiaoling Wang

Language-Codec: Bridging Discrete Codec Representations and Speech Language Models (2025.acl-long)

Challenge:	Besides Transformers without position encodings, the success of NoPE provides a new way to overcome the challenge of generalizing to longer sentences.
Approach:	They propose a parameter-efficient tuning for searching attention heads’ best temperature hyper-parameters, which substantially expands NoPE’s context size.
Outcome:	The proposed tuning significantly expands NoPE's context size, allowing it to generalize to longer sentences with state-of-the-art generalization algorithms.

Copied to clipboard

Shengpeng Ji, Minghui Fang, Jialong Zuo, Ziyue Jiang, Dingdong Wang, Hanting Wang, Hai Huang, Zhou Zhao

Towards Medical Complex Reasoning with LLMs through Medical Verifiable Problems (2025.findings-acl)

Challenge:	Existing gaps between discrete acoustic codecs and downstream speech language models . initial channel of codebooks contains excessive information, making it difficult to generate tokens from weakly supervised signals such as text.
Approach:	They propose a discrete acoustic codec for generating acustic tokens from weakly supervised signals.
Outcome:	The proposed language-codec outperforms competing audio compression algorithms and validates on downstream speech language models.

Copied to clipboard

Junying Chen, Zhenyang Cai, Ke Ji, Xidong Wang, Wanlong Liu, Rongsheng Wang, Benyou Wang

LM-Infinite: Zero-Shot Extreme Length Generalization for Large Language Models (2024.naacl-long)

Challenge:	OpenAI o1 has been a significant milestone in large language model development . however, most research in reasoning has focused on mathematical tasks . medical domains require robust reasoning to provide reliable answers .
Approach:	They propose a method to verify medical reasoning using a medical verifier . they also propose RL and reinforcement learning to enhance reasoning .
Outcome:	The proposed method outperforms general and medical-specific baselines using only 40K verifiable problems.

Copied to clipboard

Chi Han, Qifan Wang, Hao Peng, Wenhan Xiong, Yu Chen, Heng Ji, Sinong Wang

A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discovery (2024.emnlp-main)

Challenge:	Currently, large language models (LLMs) train on short text segments due to the computational overhead quadratic in the input lengths of their Transformer architectures.
Approach:	They propose a method that allows LLMs pre-trained with 2K or 4K-long segments to generalize to up to 200M length inputs while retaining perplexity.
Outcome:	The proposed method achieves 2.7 decoding speed up and 7.5 memory saving over the original model.

Copied to clipboard

Yu Zhang, Xiusi Chen, Bowen Jin, Sheng Wang, Shuiwang Ji, Wei Wang, Jiawei Han

Entailment-Preserving First-order Logic Representations in Natural Language Entailment (2025.acl-long)

Challenge:	Existing surveys on scientific LLMs focus on one or two fields or a single modality.
Approach:	They survey 260 scientific LLMs and examine their architectures and pre-training techniques . they also discuss commonalities and differences between LLM architectures .
Outcome:	The proposed model architectures and evaluation techniques are used to improve scientific discovery.

Copied to clipboard

Jinu Lee, Qi Liu, Runzhi Ma, Vincent Han, Ziqi Wang, Heng Ji, Julia Hockenmaier

Representation Learning

Challenge:	First-order logic (FOL) is often used to represent logical entailment, but determining natural language (NL) enanglement using FOL remains a challenge.
Approach:	They propose an Entailment-Preserving FOL representations task and a method which trains an NL-to-FOL translator by using the natural language entailment labels as verifiable rewards.
Outcome:	The proposed method achieves 1.8–2.7% improvement in EPR and 17.4–20.6% increase in E PR@16 compared to baselines in three datasets.

The Future is not One-dimensional: Complex Event Schema Induction by Graph Modeling for Event Prediction (2021.emnlp-main)

Copied to clipboard

Manling Li, Sha Li, Zhenhailong Wang, Lifu Huang, Kyunghyun Cho, Heng Ji, Jiawei Han, Clare Voss

Democratizing LLMs: An Exploration of Cost-Performance Trade-offs in Self-Refined Open-Source Models (2023.findings-emnlp)

Challenge:	Event schemas encode knowledge of stereotypical structures of events and their connections . previous work on event schema induction focuses on atomic events or linear temporal sequences .
Approach:	They propose a Temporal Complex Event Schema: a graph-based schema representation that encompasses events, arguments, temporal connections and argument relations.
Outcome:	The proposed model outperforms existing models on HITS@1 by 17.8%.

Copied to clipboard

Sumuk Shashidhar, Abhinav Chinta, Vaibhav Sahai, Zhenhailong Wang, Heng Ji

Rehearsal-free Continual Language Learning via Efficient Parameter Isolation (2023.acl-long)

Challenge:	Large Language Models (LLMs) have been experiencing seismic growth in size and capabilities, radically transforming the field of NLP.
Approach:	They propose a generalized variant of iterative self-critique and self-refinement devoid of external influence and a ranking metric to find the optimal model for a given task considering refined performance and cost.
Outcome:	The proposed model improves 8.2% from baseline and even with extremely small memory footprints, outperforms ChatGPT post-refinement.

Copied to clipboard

Zhicheng Wang, Yufang Liu, Tao Ji, Xiaoling Wang, Yuanbin Wu, Congcong Jiang, Ye Chao, Zhencong Han, Ling Wang, Xu Shao, Wenqiu Zeng

Enhancing Hyperbole and Metaphor Detection with Their Bidirectional Dynamic Interaction and Emotion Knowledge (2025.acl-long)

Challenge:	Existing methods for learning continual tasks do not cache history data, which makes the problem more challenging.
Approach:	They propose a method that allocates a small portion of private parameters and learns them with a shared pre-trained model.
Outcome:	The proposed method is comparable to existing methods and comparable to those using historical data.

Copied to clipboard

Li Zheng, Sihang Wang, Hao Fei, Zuquan Peng, Fei Li, Jianming Fu, Chong Teng, Donghong Ji

Sentiment Analysis

Challenge:	Existing methods for hyperbole and metaphor detection focus on superficial text features, ignoring the associations of hyperbola and metaphor . Existing frameworks focus on identifying superficial text, focusing on superficial features .
Approach:	They propose an emotion-guided hyperbole and metaphor detection framework based on bidirectional dynamic interaction.
Outcome:	The proposed framework outperforms baseline methods on four datasets.

Unlocking LLMs’ Self-Improvement Capacity with Autonomous Learning for Domain Adaptation (2025.findings-acl)

Copied to clipboard

Ke Ji, Junying Chen, Anningzhe Gao, Wenya Xie, Xiang Wan, Benyou Wang

Language Model Pre-Training with Sparse Latent Typing (2022.emnlp-main)

Challenge:	Existing models that use self-supervised and instruction fine-tuning can be trained using unlabeled corpora.
Approach:	They propose to use unlabeled target corpora to adapt large language models to new domains . they propose to employ self-supervised pre-training and instruction fine-tuning methods .
Outcome:	The proposed model can adapt to new domains using only a large amount of unlabeled target corpora.

Copied to clipboard

Liliang Ren, Zixuan Zhang, Han Wang, Clare Voss, ChengXiang Zhai, Heng Ji

The Microsoft Toolkit of Multi-Task Deep Neural Networks for Natural Language Understanding (2020.acl-demos)

Challenge:	Modern large-scale Pre-trained Language Models focus on text reconstruction, but have not sought to learn latent-level interpretable representations of sentences.
Approach:	They propose a new pre-training objective that enables the model to learn latent types . the objective allows the model a self-supervised way to extract sentence-level keywords .
Outcome:	The proposed model learns interpretable latent type categories without external knowledge and improves downstream tasks.

Copied to clipboard

Xiaodong Liu, Yu Wang, Jianshu Ji, Hao Cheng, Xueyun Zhu, Emmanuel Awa, Pengcheng He, Weizhu Chen, Hoifung Poon, Guihong Cao, Jianfeng Gao

MMedAgent: Learning to Use Medical Tools with Multi-modal Agent (2024.findings-emnlp)

Challenge:	MT-DNN is an open-source natural language understanding toolkit . it allows researchers and developers to train customized deep learning models .
Approach:	They present MT-DNN, an open-source natural language understanding toolkit . it is designed to facilitate rapid customization for a broad spectrum of NLU tasks . MT supports multi-task knowledge distillation, which can substantially compress a deep neural model without significant performance drop.
Outcome:	The proposed model can significantly compress a large model without significant performance drop.

Copied to clipboard

Binxu Li, Tiankai Yan, Yuanting Pan, Jie Luo, Ruiyang Ji, Jiayuan Ding, Zhe Xu, Shilong Liu, Haoyu Dong, Zihao Lin, Yixin Wang

Preserving Knowledge Invariance: Rethinking Robustness Evaluation of Open Information Extraction (2023.emnlp-main)

Challenge:	Multi-modal Large Language Models (MLLMs) exhibit limited generality and often fall short when compared to specialized models.
Approach:	They propose a multi-modal medical agent that picks the most suitable medical tools based on user inputs.
Outcome:	The proposed agent performs better than open-source models and the closed-source model, GPT-4o.

Copied to clipboard

Ji Qi, Chuchun Zhang, Xiaozhi Wang, Kaisheng Zeng, Jifan Yu, Jinxin Liu, Lei Hou, Juanzi Li, Xu Bin

DALR: Dual-level Alignment Learning for Multimodal Sentence Representation Learning (2025.findings-acl)

Challenge:	Existing evaluation benchmarks focus on pairwise matching, ignoring robustness . current models exhibit frustrating degradation, with a maximum drop of 23.43 F1 score .
Approach:	They propose a benchmark that simulates the evaluation of open information extraction models in the real world . they perform experiments on typical models published in the last decade and a representative large language model .
Outcome:	The proposed model is rated robust on a knowledge-invariant clique with different syntactic and expressive forms.

Copied to clipboard

Kang He, Yuzhe Ding, Haining Wang, Fei Li, Chong Teng, Donghong Ji

Efficient Attentions for Long Document Summarization (2021.naacl-main)

Challenge:	Existing multimodal sentence representation learning methods focus on aligning images and text at a coarse level, resulting in cross-modal misalignment bias and intra-modal semantic divergence.
Approach:	They propose a dual-level alignment learning framework for multimodal sentence representation learning that promotes cross-modal and intra-modal alignment.
Outcome:	The proposed framework outperforms state-of-the-art methods on semantic textual similarity and transfer tasks on semantic similarity, ranking distillation and global intra-modal alignment learning.

Copied to clipboard

Luyang Huang, Shuyang Cao, Nikolaus Parulian, Heng Ji, Lu Wang

Multi-Modal Knowledge Graph Transformer Framework for Multi-Modal Entity Alignment (2023.findings-emnlp)

Challenge:	Existing models that use full attentions have quadratic computational and memory complexities, and are too costly for long documents.
Approach:	They propose an efficient encoder-decoder attention with head-wise positional strides to effectively pinpoint salient information from the source.
Outcome:	The proposed model can process ten times more tokens than current models that use full attentions.

Copied to clipboard

Qian Li, Cheng Ji, Shu Guo, Zhaoji Liang, Lihong Wang, Jianxin Li

From Word to World: Can Large Language Models be Implicit Text-based World Models? (2026.acl-long)

Challenge:	Multi-modal entity alignment (MMEA) is a critical task that aims to identify equivalent entity pairs across multi-modal knowledge graphs (MMKGs).
Approach:	They propose a novel MMEA transformer that hierarchically introduces neighbor features, multi-modal attributes, and entity types to enhance alignment task.
Outcome:	The proposed transformer hierarchically introduces neighbor features, multi-modal attributes, and entity types to enhance the alignment task.

Copied to clipboard

Yixia Li, Hongru Wang, Jiahao Qiu, Zhenfei Yin, Dongdong Zhang, Cheng Qian, Zeping Li, Xiaoteng Ma, Guanhua Chen, Heng Ji

Bayesian Example Selection Improves In-Context Learning for Speech, Text and Visual Modalities (2024.emnlp-main)

Challenge:	Agentic learning increasingly hinges on interaction, yet real-world experience is expensive, limited, and often irreversible at inference time.
Approach:	They propose a framework that reframes language modeling as next-state prediction under interaction.
Outcome:	The proposed framework evaluates world models in text-based environments . it shows that sufficiently trained models capture coherent environment dynamics .

Copied to clipboard

Siyin Wang, Chao-Han Yang, Ji Wu, Chao Zhang

Making Pre-trained Language Models both Task-solvers and Self-calibrators (2023.findings-acl)

Challenge:	Large language models (LLMs) can adapt to new tasks easily and efficiently in a training-free manner.
Approach:	They propose to use eBayesian in-context example selection method to extend the inference probability conditioned on in-constitut examples based on Bayes’ theorem to select in-strategy examples . Experimental results show the efficacy and robustness of their method on various models, tasks and modalities.
Outcome:	The proposed method is based on the eBayesian in-context example selection approach.

Copied to clipboard

Yangyi Chen, Xingyao Wang, Heng Ji

Reaction Miner: An Integrated System for Chemical Reaction Extraction from Textual Data (2023.emnlp-demo)

Challenge:	Existing work shows that pre-trained language models can be effective for high-stake applications, but they become overconfident in their wrong predictions.
Approach:	They propose to use extra data to train pre-trained language models to effectively utilize training samples to make them both task-solvers and self-calibrators.
Outcome:	The proposed method can be used in three downstream applications, including selective classification, adversarial defense, and model cascading.

Copied to clipboard

Ming Zhong, Siru Ouyang, Yizhu Jiao, Priyanka Kargupta, Leo Luo, Yanzhen Shen, Bobby Zhou, Xianrui Zhong, Xuan Liu, Hongxiang Li, Jinfeng Xiao, Minhao Jiang, Vivian Hu, Xuan Wang, Heng Ji, Martin Burke, Huimin Zhao, Jiawei Han

LORE: Continual Logit Rewriting Fosters Faithful Generation (2025.findings-emnlp)

Challenge:	Reaction Miner is a system designed to extract chemical reactions from raw scientific PDFs.
Approach:	They propose a system that extracts chemical reactions directly from raw scientific PDFs.
Outcome:	The proposed system can extract chemical reactions from raw scientific PDFs.

Copied to clipboard

Charles Yu, Qingyun Wang, Yuting Hu, Jinjun Xiong, Heng Ji

Early Exit with Disentangled Representation and Equiangular Tight Frame (2023.findings-acl)

Challenge:	Using aspect-oriented summarization as a case study, we propose LOgit REwriting, a new controlled generation paradigm which can be faithful to external knowledge and to the LLM’s intentions.
Approach:	They propose a controlled generation paradigm which can be faithful to external knowledge and to the LLM's intentions.
Outcome:	The proposed paradigm can be faithful to external knowledge and to the LLM's intentions while balancing that with accuracy.

Copied to clipboard

Yixin Ji, Jikai Wang, Juntao Li, Qiang Chen, Wenliang Chen, Min Zhang

Representation Learning

Challenge:	Existing early exit paradigm relies on training parametrical internal classifiers to complete specific tasks.
Approach:	They propose a method to decouple two distinct types of representation and introduce a non-parametric tight frame classifier for improvement.
Outcome:	Experiments on monolingual and multilingual tasks show that the proposed method improves over existing methods.

NewsClaims: A New Benchmark for Claim Detection from News with Attribute Knowledge (2022.emnlp-main)

Copied to clipboard

Revanth Gangi Reddy, Sai Chetan Chinthakindi, Zhenhailong Wang, Yi Fung, Kathryn Conger, Ahmed ELsayed, Martha Palmer, Preslav Nakov, Eduard Hovy, Kevin Small, Heng Ji

Explore the Reasoning Capability of LLMs in the Chess Testbed (2025.naacl-short)

Challenge:	Current claims detection methods focus on sentence analysis, ignoring other attributes . a key element of identifying misinformation is detecting the claims and the arguments that have been presented.
Approach:	They propose a benchmark for attribute-aware claim detection in the news domain . they extend the problem to include extraction of additional attributes related to each claim .
Outcome:	The proposed system performs well on the test, but human performance is still poor.

Copied to clipboard

Shu Wang, Lei Ji, Renxi Wang, Wenxiao Zhao, Haokun Liu, Yifan Hou, Ying Nian Wu

Soft Knowledge Prompt: Help External Knowledge Become a Better Teacher to Instruct LLM in Knowledge-based VQA (2024.acl-long)

Challenge:	a recent study shows that large language models struggle with long-term, complex reasoning tasks.
Approach:	They propose to integrate annotated strategy and tactic into large language models to improve reasoning capability.
Outcome:	The proposed model performs better than GPT, Claude, and Gemini models . it integrates annotated strategy and tactic into the model .

Copied to clipboard

Qunbo Wang, Ruyi Ji, Tianhao Peng, Wenjun Wu, Zechao Li, Jing Liu

Browse and Concentrate: Comprehending Multimodal Content via Prior-LLM Context Fusion (2024.acl-long)

Challenge:	Recent research focuses on improving prediction performance and reliability of LLM.
Approach:	They propose a method to actively extract valuable information from the knowledge to produce a latent vector as a soft prompt, which is fused with the image embedding to form a knowledge-enhanced context to instruct LLM.
Outcome:	The proposed method improves performance on knowledge-based VQA benchmarks.

Copied to clipboard

Ziyue Wang, Chi Chen, Yiqi Zhu, Fuwen Luo, Peng Li, Ming Yan, Ji Zhang, Fei Huang, Maosong Sun, Yang Liu

Mitigating the Alignment Tax of RLHF (2024.emnlp-main)

Challenge:	Multimodal Large Language Models (MLLMs) lack understanding of multi-image and interleaved inputs due to the visual features encoded by frozen encoders before being fed into the LLM backbone.
Approach:	They propose a two phase paradigm to enable in-depth multimodal context fusion prior to feeding the features into LLMs.
Outcome:	The proposed paradigm boosts the performance on 7 multi-image scenarios, contributing to increments on average accuracy by 2.13% and 7.60% against strong MLLMs baselines with 3B and 11B LLMs, respectively.

Copied to clipboard

Yong Lin, Hangyu Lin, Wei Xiong, Shizhe Diao, Jianmeng Liu, Jipeng Zhang, Rui Pan, Haoxiang Wang, Wenbin Hu, Hanning Zhang, Hanze Dong, Renjie Pi, Han Zhao, Nan Jiang, Heng Ji, Yuan Yao, Tong Zhang

Zero- and Few-Shot Event Detection via Prompt-Based Meta Learning (2023.acl-long)

Challenge:	Large Language Models (LLMs) acquire a wide range of abilities during pre-training, but aligning LLMs under Reinforcement Learning with Human Feedback (RLHF) can lead to forgetting pretrained abilities, which is also known as the alignment tax.
Approach:	They propose to use a model averaging technique to find the most powerful alignment-forging Pareto front among RLHF algorithms.
Outcome:	The proposed method achieves the strongest alignment-forging Pareto front among competing methods.

Copied to clipboard

Zhenrui Yue, Huimin Zeng, Mengfei Lan, Heng Ji, Dong Wang

Towards Injecting Medical Visual Knowledge into Multimodal LLMs at Scale (2024.emnlp-main)

Challenge:	Existing methods for event detection often fail to detect unseen or rare events due to the lack of domain knowledge.
Approach:	They propose a meta learning-based framework for zero-shot event detection that uses a prompt-based prompt and a trigger-aware soft verbalizer to efficiently project output to unseen tasks.
Outcome:	The proposed framework performs state-of-the-art in zero-shot and few-shot scenarios on benchmark datasets FewEvent and MAVEN.

Copied to clipboard

Junying Chen, Chi Gui, Ruyi Ouyang, Anningzhe Gao, Shunian Chen, Guiming Chen, Xidong Wang, Zhenyang Cai, Ke Ji, Xiang Wan, Benyou Wang

Word Reordering for Zero-shot Cross-lingual Structured Prediction (2021.emnlp-main)

Challenge:	Multimodal large language models (MLLMs) lack visual knowledge in medical applications due to data privacy concerns and high annotation costs.
Approach:	They refined medical image-text pairs from PubMed and employed MLLMs (GPT-4V) to denoise and reformat the data.
Outcome:	The proposed model significantly improves the MMMU Health & Medicine track and shows that it can be used in multimodal scenarios.

Copied to clipboard

Tao Ji, Yong Jiang, Tao Wang, Zhongqiang Huang, Fei Huang, Yuanbin Wu, Xiaoling Wang

Low-Resource NLP

Challenge:	Current sentence encoders are word order sensitive, resulting in poor performance . Adapting word order from one language to another is key in cross-lingual structured prediction.
Approach:	They propose a new module to organize words following the source language order . they build structured prediction models with bag-of-words inputs and introduce a module to do this .
Outcome:	The proposed model significantly improves target language performance for languages that are distant from the source language.

Simple and Effective Graph-to-Graph Annotation Conversion (2022.coling-1)

Copied to clipboard

Yuxuan Wang, Zhilin Lei, Yuqiu Ji, Wanxiang Che

DeepMaven: Deep Question Answering on Long-Distance Movie/TV Show Videos with Multimedia Knowledge Extraction and Synthesis (2023.eacl-main)

Challenge:	Existing work on graph-structured annotation conversions has focused on feature-based models which are not easily applicable to new conversions.
Approach:	They propose two graph-to-graph conversion approaches which use pseudo data and inherit parameters to guide conversions respectively.
Outcome:	The proposed approaches outperform strong baselines with higher conversion score on a graph-structured dataset and other datasets.

Copied to clipboard

Yi Fung, Han Wang, Tong Wang, Ali Kebarighotbi, Mohit Bansal, Heng Ji, Prem Natarajan

SciMON: Scientific Inspiration Machines Optimized for Novelty (2024.acl-long)

Challenge:	Long video content understanding poses a challenging set of research questions as it involves long-distance, cross-media reasoning and knowledge awareness.
Approach:	They propose a framework which extracts events, entities, and relations from the rich multimedia content in long videos to pre-construct movie knowledge graphs.
Outcome:	The proposed framework performs competitively for both the new DeepMovieQA and the pre-existing MovieQA dataset.

Copied to clipboard

Qingyun Wang, Doug Downey, Heng Ji, Tom Hope

DeepMed: Building a Medical DeepResearch Agent via Multi-hop Med-Search Data and Turn-Controlled Agentic Training & Inference (2026.findings-acl)

Challenge:	Existing literature-based hypothesis generation models focus on binary link prediction, limiting expressivity of hypotheses.
Approach:	They propose a framework that uses literature-based hypothesis generation as input . they use literature-derived literature as background and output natural language ideas .
Outcome:	The proposed model improves the ability of language models to generate new scientific directions grounded in literature.

Copied to clipboard

Zihan Wang, Hao Wang, Shi Feng, Xiaocui Yang, Daling Wang, Yiqun Zhang, Jinghao Lin, Xiaozhong Ji, Haihua Yang

MIMIR: A Customizable Agent Tuning Platform for Enhanced Scientific Applications (2024.emnlp-demo)

Challenge:	Medical reasoning models are constrained by parametric knowledge and can induce hallucinations and spurious attributions.
Approach:	They propose a model that uses a multi-hop med-search QA synthesis method to apply the DR paradigm in medical contexts.
Outcome:	The proposed model outperforms larger medical reasoning models on medical benchmarks.

Copied to clipboard

Xiangru Tang, Chunyuan Deng, Hanminwang Hanminwang, Haoran Wang, Yilun Zhao, Wenqi Shi, Yi Fung, Wangchunshu Zhou, Jiannan Cao, Heng Ji, Arman Cohan, Mark Gerstein

The Shifted and The Overlooked: A Task-oriented Investigation of User-GPT Interactions (2023.emnlp-main)

Challenge:	Large language models (LLMs) have evolved into interactive agents capable of planning, tool use, and task execution across various tasks.
Approach:	They propose a platform that leverages large language models to generate agent-tuning data for fine-tuneing smaller, specialized models.
Outcome:	MIMIR enables large models to simulate various roles and create interaction data, which can then be used to fine-tune open-source models like LLaMA2.

Copied to clipboard

Siru Ouyang, Shuohang Wang, Yang Liu, Ming Zhong, Yizhu Jiao, Dan Iter, Reid Pryzant, Chenguang Zhu, Heng Ji, Jiawei Han

SafeMCP: Proactive Power Regulation for LLM Agent Defense via Environment-Grounded Look-Ahead Reasoning (2026.acl-long)

Challenge:	Recent advances in large language models (LLMs) have produced models that exhibit remarkable performance across a variety of NLP tasks.
Approach:	They analyze a large-scale collection of user-GPT conversations to identify a significant gap between academic research in NLP and the needs of real-world NLP applications.
Outcome:	The proposed model outperforms existing models in a large-scale collection of user-GPT conversations and identifies a significant gap between the tasks that users frequently request from LLMs and the tasks commonly studied in academic research.

Copied to clipboard

Lichao Wang, ZhaoXing Ren, Tianzhuo Yang, Jiaming Ji, Chi Harold Liu, Yaodong Yang, Juntao Dai

DUAL RM: Beyond Rule-based Preference Reward Modeling via Meta-Reward (2026.acl-long)

Challenge:	Large Language Model (LLM) agents are expanding their action spaces to operate in complex environments.
Approach:	They propose a server-side defense plugin that constrains tool acquisition via predictive reasoning regarding future safety risks.
Outcome:	Experiments on PowerSeeking Bench, ToolEmu, and AgentHarm show that SafeMCP achieves a safe equilibrium, effectively mitigating risks while preserving agent utility.

Copied to clipboard

Xiaobo Liang, Wanfu Wang, Qipeng Huang, Yuyang Ding, Zecheng Tang, Yixin Ji, Qianben Chen, Zhe Zhao, Kehai Chen, Juntao Li, Min Zhang

Challenge:	Existing preference-based reward modeling methods face a recursive dependency where each verifier requires a meta-verifier, leading to continuous and costly dependence on human annotation.
Approach:	They propose a dual RM that couples discriminative and generative reward models under a non-parametric meta-reward.
Outcome:	The proposed model achieves strong performance across major preference benchmarks and even when trained exclusively on language modality, it exhibits robust cross-modal transfer on Omni-RewardBench.

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

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

Generative Music Models’ Alignment with Professional and Amateur Users’ Expectations (2025.findings-acl)

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

Zihao Wang, Jiaxing Yu, Haoxuan Liu, Zehui Zheng, Yuhang Jin, Shuyu Li, Shulei Ji, Kejun Zhang

The Role of Visual Modality in Multimodal Mathematical Reasoning: Challenges and Insights (2025.acl-long)

Challenge:	Recent years have witnessed rapid advances in text-to-music generation using large language models.
Approach:	They propose a task to align AI-generated music with human expressions . they use a dataset of over 1.5 million songs to analyze their content .
Outcome:	The proposed framework outperforms baseline models and facilitates end-to-end generation of songs audio.

Copied to clipboard

Yufang Liu, Yao Du, Tao Ji, Jianing Wang, Yang Liu, Yuanbin Wu, Aimin Zhou, Mengdi Zhang, Xunliang Cai

Can Language Models Follow Multiple Turns of Entangled Instructions? (2025.findings-emnlp)

Challenge:	Existing models that leverage visual information do not improve math reasoning performance . authors suggest that visual information is important for multimodal reasoning .
Approach:	They propose a dataset to require image reliance for problem-solving and challenge models with similar, yet distinct, images that change the correct answer.
Outcome:	The proposed model performance is unaffected by changes to or removal of images in the dataset.

Copied to clipboard

Chi Han, Xin Liu, Haodong Wang, Shiyang Li, Jingfeng Yang, Haoming Jiang, Zhengyang Wang, Qingyu Yin, Liang Qiu, Changlong Yu, Yifan Gao, Zheng Li, Bing Yin, Jingbo Shang, Heng Ji

Knowledge-Enriched Natural Language Generation (2021.emnlp-tutorials)

Challenge:	Despite of significant achievements in improving instruction-following capabilities of large language models, the ability to process multiple potentially entangled or conflicting instructions remains a considerable challenge.
Approach:	They construct multi-turn instruction with 1.1K high-quality multi-turned conversations using the human-in-the-loop approach and examine their capabilities.
Outcome:	The proposed model shows that it is difficult to integrate multiple turns and balance competing objectives when instructions intersect or conflict.

Copied to clipboard

Wenhao Yu, Meng Jiang, Zhiting Hu, Qingyun Wang, Heng Ji, Nazneen Rajani

TAG: Gradient Attack on Transformer-based Language Models (2021.findings-emnlp)

Challenge:	Knowledge-enriched text generation poses unique challenges in modeling and learning . a roadmap will outline the state-of-the-art methods to tackle these challenges .
Approach:	They propose a roadmap to tackle the challenges of knowledge-enriched text generation . they will dive deep into various technical components to illustrate how to represent knowledge .
Outcome:	This tutorial outlines the state-of-the-art methods to tackle the problem . it aims to show how to represent knowledge, feed knowledge into a generation model, evaluate results .

Copied to clipboard

Jieren Deng, Yijue Wang, Ji Li, Chenghong Wang, Chao Shang, Hang Liu, Sanguthevar Rajasekaran, Caiwen Ding

EMCompress: Video-LLMs with Endomorphic Multimodal Compression (2026.findings-acl)

Challenge:	Recent studies show that publicly shared gradients in the training process can reveal the private training data to a third-party.
Approach:	They propose a gradient attack algorithm to reconstruct the local training data using GLUE benchmarks.
Outcome:	The proposed algorithm achieves 1.5x recover rate and 2.5x ROUGE-2 over previous methods without the need of ground truth label.

Copied to clipboard

Zheyu Fan, Jiateng Liu, Yuji Zhang, Zihan Wang, Yi R. Fung, Manling Li, Heng Ji

RAG-Instruct: Boosting LLMs with Diverse Retrieval-Augmented Instructions (2025.emnlp-main)

Challenge:	Static, sparse frame sampling either dilutes evidence across task-irrelevant segments at significant cost or misses fine-grained temporal semantics altogether.
Approach:	They propose a novel task that compresses multimodal input while preserving answer invariance across reasonable downstream models.
Outcome:	The proposed task surpasses prior methods by 0.40 F-1 with competitive query rewriting.

Copied to clipboard

Wanlong Liu, Junying Chen, Ke Ji, Li Zhou, Wenyu Chen, Benyou Wang

Information Retrieval

Challenge:	Retrieval-Augmented Generation (RAG) has emerged as a key paradigm for enhancing large language models by incorporating external knowledge.
Approach:	They propose a method for synthesizing diverse and high-quality RAG instruction data based on any source corpus.
Outcome:	The proposed method outperforms existing methods in multiple tasks and achieves strong zero-shot performance.

VisPCO: Visual Token Pruning Configuration Optimization via Budget-Aware Pareto-Frontier Learning for Vision-Language Models (2026.acl-long)

Copied to clipboard

Huawei Ji, Yuanhao Sun, Yuan Jin, Cheng Deng, Jiaxin Ding, Luoyi Fu, Xinbing Wang

PALT: Parameter-Lite Transfer of Language Models for Knowledge Graph Completion (2022.findings-emnlp)

Challenge:	Existing methods for visual token pruning rely on predefined configurations without determining whether they achieve optimal performance.
Approach:	They propose a framework that formulates visual token pruning as a Pareto configuration optimization problem to automatically identify optimal configurations.
Outcome:	The proposed framework approximates the empirical Pareto frontier obtained through grid search and generalizes well across pruning methods and VLM architectures.

Copied to clipboard

Jianhao Shen, Chenguang Wang, Ye Yuan, Jiawei Han, Heng Ji, Koushik Sen, Ming Zhang, Dawn Song

Adaptive Feature-based Low-Rank Compression of Large Language Models via Bayesian Optimization (2024.findings-emnlp)

Challenge:	Pretrained language models (LMs) are a powerful transfer learning approach for knowledge graph (KG) completion.
Approach:	They propose a parameter-lite transfer learning approach for pretrained language models for knowledge graph (KG) completion.
Outcome:	The proposed model outperforms the state-of-the-art models on a knowledge graph completion benchmark by tuning 1% of the parameters.

Copied to clipboard

Yixin Ji, Yang Xiang, Juntao Li, Qingrong Xia, Zi Ye, Xinyu Duan, Zhefeng Wang, Kehai Chen, Min Zhang

Code4Struct: Code Generation for Few-Shot Event Structure Prediction (2023.acl-long)

Challenge:	Large language models require a balance between efficiency and performance.
Approach:	They propose a low-rank compression technique that reduces non-essential parameters by decomposing weight matrices into products of two low-ranked matrici.
Outcome:	The proposed method outperforms existing pruning and low-rank compression techniques in maintaining model performance at the same compression ratio.

Copied to clipboard

Xingyao Wang, Sha Li, Heng Ji

GradOT: Training-free Gradient-preserving Offsite-tuning for Large Language Models (2025.acl-long)

Challenge:	Large Language Models (LLMs) trained on a mixture of text and code have demonstrated impressive capability in translating natural language (NL) into structured code.
Approach:	They propose to use programming language (PL) inheritance and type annotations to translate text into code to tackle structured prediction tasks.
Outcome:	The proposed model outperforms existing models on 20-shot data by 29.5% absolute F1.

Copied to clipboard

Kai Yao, Zhaorui Tan, Penglei Gao, Lichun Li, Kaixin Wu, Yinggui Wang, Yuan Zhao, Yixin Ji, Jianke Zhu, Wei Wang

Convert Language Model into a Value-based Strategic Planner (2025.acl-industry)

Challenge:	Existing methods for offsite-tuning of large language models require high computational costs and lack theoretical analysis.
Approach:	They propose an offsite-tuning approach that selectively applies compression techniques such as rank compression and channel pruning to preserve the gradients of fine-tuned adapters while ensuring privacy.
Outcome:	The proposed method surpasses existing OT methods in privacy protection and model performance.

Copied to clipboard

Xiaoyu Wang, Yue Zhao, Qingqing Gu, Zhonglin Jiang, Yong Chen, Luo Ji

RESIN: A Dockerized Schema-Guided Cross-document Cross-lingual Cross-media Information Extraction and Event Tracking System (2021.naacl-demos)

Challenge:	Emotional support conversation (ESC) aims to alleviate the emotional distress of individuals through effective conversations.
Approach:	They propose a framework that bootstraps the planning during ESC and determines the optimal strategy based on long-term returns.
Outcome:	The proposed framework outperforms baseline models on ESC datasets and can be used to guide the LLM to response.

Copied to clipboard

Haoyang Wen, Ying Lin, Tuan Lai, Xiaoman Pan, Sha Li, Xudong Lin, Ben Zhou, Manling Li, Haoyu Wang, Hongming Zhang, Xiaodong Yu, Alexander Dong, Zhenhailong Wang, Yi Fung, Piyush Mishra, Qing Lyu, Dídac Surís, Brian Chen, Susan Windisch Brown, Martha Palmer, Chris Callison-Burch, Carl Vondrick, Jiawei Han, Dan Roth, Shih-Fu Chang, Heng Ji

Dual-Gated Fusion with Prefix-Tuning for Multi-Modal Relation Extraction (2023.findings-acl)

Challenge:	We present a new information extraction system that can construct temporal event graphs from news documents.
Approach:	They propose a temporal event graph extraction system that can extract news documents . they extend the system from sentence-level event extraction to cross-document cross-media event extraction .
Outcome:	The proposed system can extract temporal event graphs from news documents in multiple languages and multiple data modalities.

Copied to clipboard

Qian Li, Shu Guo, Cheng Ji, Xutan Peng, Shiyao Cui, Jianxin Li, Lihong Wang

Typology Guided Multilingual Position Representations: Case on Dependency Parsing (2023.findings-acl)

Challenge:	Existing methods for multi-modal relation extraction lack useful visual information.
Approach:	They propose a novel multi-modal relation extraction framework to capture deeper correlations of text, entity pair, and image/objects.
Outcome:	The proposed framework captures the deeper correlations of text, entity pair, and image/objects, and extracts useful information.

Copied to clipboard

Tao Ji, Yuanbin Wu, Xiaoling Wang

Syntactic Text Processing

Challenge:	Recent multilingual models benefit from strong unified semantic representation models, but conflicting linguistic regularities may break the effectiveness of word position features in multilingual learning.
Approach:	They propose to combine prior knowledge from typology features and existing position vectors to create a position generation network which combines prior knowledge of a language's position space and typological characterization.
Outcome:	The proposed model can achieve the best multilingual parsing results by combining prior knowledge from typology features and existing position vectors.

MIRTT: Learning Multimodal Interaction Representations from Trilinear Transformers for Visual Question Answering (2021.findings-emnlp)

Copied to clipboard

Junjie Wang, Yatai Ji, Jiaqi Sun, Yujiu Yang, Tetsuya Sakai

Schema-Guided Culture-Aware Complex Event Simulation with Multi-Agent Role-Play (2024.emnlp-demo)

Challenge:	Existing bilinear methods focus on inter-modality information between images and questions . existing models focus on the interaction between images, questions, and images .
Approach:	They propose a trilinear interaction framework that incorporates attention mechanisms for capturing inter-modality and intra-modal relationships.
Outcome:	The proposed model outperforms bilinear models on the Visual7W Telling task and VQA-1.0 Multiple Choice task and outperformed baselines on the VQA, TDIUC and GQA datasets.

Copied to clipboard

Sha Li, Revanth Gangi Reddy, Khanh Nguyen, Qingyun Wang, Yi Fung, Chi Han, Jiawei Han, Kartik Natarajan, Clare Voss, Heng Ji

Challenge:	Complex news events require swift responses from government and society, authors say . relying on historical events to project the future is insufficient, they say - a simulator for complex news events is needed .
Approach:	They propose a controllable complex news event simulator guided by event schema and user-provided assumptions . they incorporate a geo-diverse commonsense and cultural norm-aware knowledge enhancement component .
Outcome:	The proposed simulator achieves higher coherence and appropriateness than existing models.

RESIN-11: Schema-guided Event Prediction for 11 Newsworthy Scenarios (2022.naacl-demo)

Copied to clipboard

Xinya Du, Zixuan Zhang, Sha Li, Pengfei Yu, Hongwei Wang, Tuan Lai, Xudong Lin, Ziqi Wang, Iris Liu, Ben Zhou, Haoyang Wen, Manling Li, Darryl Hannan, Jie Lei, Hyounghun Kim, Rotem Dror, Haoyu Wang, Michael Regan, Qi Zeng, Qing Lyu, Charles Yu, Carl Edwards, Xiaomeng Jin, Yizhu Jiao, Ghazaleh Kazeminejad, Zhenhailong Wang, Chris Callison-Burch, Mohit Bansal, Carl Vondrick, Jiawei Han, Dan Roth, Shih-Fu Chang, Martha Palmer, Heng Ji

Improving Consistency for Text Summarization with Energy Functions (2023.findings-emnlp)

Challenge:	Existing methods for event prediction are incomplete and noisy.
Approach:	They propose to use news-related event schemas to extract newsworthy events . they build a demo website and include a video demonstrating the framework .
Outcome:	The proposed framework can be applied to a wide variety of newsworthy scenarios.

Copied to clipboard

Qi Zeng, Qingyu Yin, Zheng Li, Yifan Gao, Sreyashi Nag, Zhengyang Wang, Bing Yin, Heng Ji, Chao Zhang

Summarization

Challenge:	Current abstractive summarization models generate inconsistent content due to the inherently noisy dataset and the discrepancy between maximum likelihood estimation based training objectives and consistency measurements.
Approach:	They propose a new consistency taxonomy that categorizes inconsistent content into faithfulness, factuality, and self-supportiveness.
Outcome:	Experiments on XSUM and CNN/DM datasets show that EnergySum mitigates the trade-off between accuracy and consistency.

Resource-Friendly Dynamic Enhancement Chain for Multi-Hop Question Answering (2025.findings-acl)

Copied to clipboard

Binquan Ji, Haibo Luo, YifeiLu YifeiLu, Lei Hei, Jiaqi Wang, Tingjing Liao, Wang Lingyu, Shichao Wang, Feiliang Ren

Natural Language Interfaces

Challenge:	Existing approaches to solve multi-hop question answering challenges require multiple rounds of retrieval and iterative generation.
Approach:	They propose a framework that decomposes complex questions into coherent subquestions . it then iteratively refines these subquests through context-aware rewriting to generate effective query formulations.
Outcome:	The proposed framework performs on par with or surpasses state-of-the-art benchmarks while significantly reducing token consumption.

Seer Self-Consistency: Advance Budget Estimation for Adaptive Test-Time Scaling (2026.findings-acl)

Copied to clipboard

Shiyu Ji, Yixuan Wang, Yijun Liu, Qingfu Zhu, Wanxiang Che

Challenge:	Large Language Models (LLMs) have demonstrated exceptional performance in reasoning tasks, particularly in mathematics.
Approach:	They propose a dynamic self-consistency framework that integrates System 1 and System 2 reasoning to improve token efficiency and latency.
Outcome:	The proposed method outperforms existing methods, achieving up to 47% reduction in token consumption and 43% reduction in inference latency without significant performance loss.

Semi-Autoregressive Neural Machine Translation (D18-1)

Copied to clipboard

Chunqi Wang, Ji Zhang, Haiqing Chen

Machine Translation

Challenge:	Existing approaches to neural machine translation are typically autoregressive but suffer from low parallelizability and thus slow at decoding long sequences.
Approach:	They propose a semi-autoregressive Transformer model for fast sequence generation that keeps the autoregressive property in global but relieves in local .
Outcome:	The proposed model achieves 5.58 speedup while maintaining 88% translation quality, significantly better than previous non-autoregressive methods.

SMART: Self-Aware Agent for Tool Overuse Mitigation (2025.findings-acl)

Copied to clipboard

Cheng Qian, Emre Can Acikgoz, Hongru Wang, Xiusi Chen, Avirup Sil, Dilek Hakkani-Tür, Gokhan Tur, Heng Ji

“I See What You Did There”: Can Large Vision-Language Models Understand Multimodal Puns? (2026.acl-long)

Challenge:	Current Large Language Models (LLMs) lack self-awareness to balance reasoning and tool use, increasing computational overhead.
Approach:	They propose a paradigm that enhances an agent’s self-awareness to optimize task handling and reduce tool overuse.
Outcome:	The proposed model reduces tool use by 24% while improving performance by over 37%.

Copied to clipboard

Naen Xu, Jiayi Sheng, Changjiang Li, Chunyi Zhou, Yuyuan Li, Tianyu Du, Jun Wang, Zhihui Fu, Jinbao Li, Shouling Ji

Towards One-to-Many Visual Question Answering (2024.findings-emnlp)

Challenge:	Puns are a common form of rhetorical wordplay that exploits polysemy and phonetic similarity to create humor.
Approach:	They propose a multimodal pun generation pipeline and a model to evaluate their understanding of puns.
Outcome:	The proposed benchmark improves the understanding of multimodal puns by 16.5% in the F1 test.

Copied to clipboard

Huishan Ji, Qingyi Si, Zheng Lin, Yanan Cao, Weiping Wang

Thinking with Map: Reinforced Parallel Map-Augmented Agent for Geolocalization (2026.findings-acl)

Challenge:	Existing Visual Question Answering systems are constrained to support domain-specific questions . a model trained on a single specific domain may not be competent for real-world application.
Approach:	They propose a task to enable a single model to answer as many different domains of questions as possible . they break the task down into the integration of three key abilities .
Outcome:	The proposed model can answer as many domains of questions as possible, the authors argue . the proposed model generalizes well to three extra zero-shot datasets, and the results are published.

Copied to clipboard

Yuxiang Ji, Yong Wang, Ziyu Ma, Yiming Hu, Hailang Huang, Xuecai Hu, Guanhua Chen, Liaoni Wu, Xiangxiang Chu

T2A-Feedback: Improving Basic Capabilities of Text-to-Audio Generation via Fine-grained AI Feedback (2025.acl-long)

Challenge:	Existing large vision-language model (LVLM) approaches overlook a common strategy used by humans — using maps.
Approach:	They propose a method to equip a vision-language model with the ability to think with maps and optimize it using agentic reinforcement learning and parallel test-time scaling.
Outcome:	The proposed method outperforms open- and closed-source models on most metrics.

Copied to clipboard

Zehan Wang, Ke Lei, Chen Zhu, Jiawei Huang, Sashuai Zhou, Luping Liu, Xize Cheng, Shengpeng Ji, Zhenhui Ye, Tao Jin, Zhou Zhao

Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration (2024.naacl-long)

Challenge:	Text-to-audio (T2A) models still struggle to satisfy human preferences for prompt-following and acoustic quality when generating complex multi-event audio.
Approach:	They propose to use AI feedback learning to enhance basic capabilities of text-to-audio models . they use a large audio preference dataset to evaluate the model's capabilities .
Outcome:	The proposed model improves in simple and complex scenarios with AI feedback learning.

Copied to clipboard

Zhenhailong Wang, Shaoguang Mao, Wenshan Wu, Tao Ge, Furu Wei, Heng Ji

Cross-Document Cross-Lingual NLI via RST-Enhanced Graph Fusion and Interpretability Prediction (2025.emnlp-main)

Challenge:	Existing work on LLMs that only enhance reasoning abilities, but which lack factual hallucination and slow-thinking capabilities, argues that SPP is a cognitive synergist.
Approach:	They propose a Solo Performance Prompting (SPP) that transforms a single LLM into a cognitive synergist by engaging in multi-turn self-collaboration with multiple personas.
Outcome:	The proposed model reduces factual hallucination and maintains strong reasoning abilities on three challenging tasks .

Copied to clipboard

Mengying Yuan, WenHao Wang, Zixuan Wang, Yujie Huang, Kangli Wei, Fei Li, Chong Teng, Donghong Ji

Explainability & Interpretability in NLP

Challenge:	Despite the development of many subdirections, Cross-Document Cross-Lingual NLI remains largely unexplored.
Approach:	They propose a novel paradigm that extends traditional NLI capabilities to multi-document, multilingual scenarios by integrating RST-enhanced graph fusion with interpretability-aware prediction.
Outcome:	The proposed method improves on existing models and document-level NLI to multi-document, multilingual scenarios.

Infogent: An Agent-Based Framework for Web Information Aggregation (2025.findings-naacl)

Copied to clipboard

Revanth Gangi Reddy, Sagnik Mukherjee, Jeonghwan Kim, Zhenhailong Wang, Dilek Hakkani-Tür, Heng Ji

COVID-19 Literature Knowledge Graph Construction and Drug Repurposing Report Generation (2021.naacl-demos)

Challenge:	Existing web navigation tasks evaluate web agents on task completion basis . however, information aggregation tasks have received relatively little attention .
Approach:	They propose a web navigation framework that uses three components for web information aggregation.
Outcome:	The proposed framework beats existing SOTA search framework by 7% under Direct API-Driven Access on FRAMES and improves over an existing information-seeking web agent by 4.3% under Interactive Visual Access on AssistantBench.

Copied to clipboard

Qingyun Wang, Manling Li, Xuan Wang, Nikolaus Parulian, Guangxing Han, Jiawei Ma, Jingxuan Tu, Ying Lin, Ranran Haoran Zhang, Weili Liu, Aabhas Chauhan, Yingjun Guan, Bangzheng Li, Ruisong Li, Xiangchen Song, Yi Fung, Heng Ji, Jiawei Han, Shih-Fu Chang, James Pustejovsky, Jasmine Rah, David Liem, Ahmed ELsayed, Martha Palmer, Clare Voss, Cynthia Schneider, Boyan Onyshkevych

CMMaTH: A Chinese Multi-modal Math Skill Evaluation Benchmark for Foundation Models (2025.coling-main)

Challenge:	a new framework to digest relevant biomedical knowledge is needed to combat COVID-19 . quantity of research results is a bottleneck, and false information promoted in publications .
Approach:	a team of researchers has developed a framework to extract multimedia knowledge elements from scientific literature to combat COVID-19.
Outcome:	a new framework extracts fine-grained multimedia knowledge elements from scientific literature . it provides detailed contextual sentences, subfigures, and knowledge subgraphs as evidence . the framework is based on a case study of drug repurposing .

Copied to clipboard

Zhongzhi Li, Ming-Liang Zhang, Pei-Jie Wang, Jian Xu, Rui-Song Zhang, Yin Fei, Zhi-Long Ji, Jin-Feng Bai, Zhen-Ru Pan, Jiaxin Zhang, Cheng-Lin Liu

Numerical Reasoning

Challenge:	Large language models excel in various language tasks, while large multimodal models effectively handle visual-language problems.
Approach:	They propose to use a multimodal multimodal model evaluation benchmark to evaluate model performance in Chinese K12 classrooms.
Outcome:	The proposed model evaluation tool is integrated with the CMMaTH dataset.

Document-Level Machine Translation with Large Language Models (2023.emnlp-main)

Copied to clipboard

Longyue Wang, Chenyang Lyu, Tianbo Ji, Zhirui Zhang, Dian Yu, Shuming Shi, Zhaopeng Tu

Dream to Chat: Model-based Reinforcement Learning on Dialogues with User Belief Modeling (2025.findings-emnlp)

Challenge:	Large language models (LLMs) such as ChatGPT can produce coherent, cohesive, relevant, and fluent answers for various natural language processing tasks.
Approach:	They examine the impact of different prompts on document-level translation quality and discourse phenomena using figures and lines, which are invisible to GPT-4.
Outcome:	The proposed models outperform commercial MT systems and advanced document-level MT methods on a number of benchmarks and show potential to become a new paradigm for document- level translation.

Copied to clipboard

Yue Zhao, Xiaoyu Wang, Dan Wang, Zhonglin Jiang, Qingqing Gu, Teng Chen, Ningyuan Xi, Jinxian Qu, Yong Chen, Luo Ji

Zemi: Learning Zero-Shot Semi-Parametric Language Models from Multiple Tasks (2023.findings-acl)

Challenge:	a framework for constructing dialogue world models for natural language tasks is currently lacking.
Approach:	They propose a framework that can be used to train a dialogue world model.
Outcome:	The proposed framework can predict future utterances and user beliefs . it can achieve state-of-the-art performance on emotion classification and sentiment identification .

Copied to clipboard

Zhenhailong Wang, Xiaoman Pan, Dian Yu, Dong Yu, Jianshu Chen, Heng Ji

COVID-19 Claim Radar: A Structured Claim Extraction and Tracking System (2022.acl-demo)

Challenge:	Existing semi-parametric language models lack the capacity to perform zero-shot tasks . large language models have shown impressive zero-shoot ability, but huge model size costs . semi-parametric language model can be used to augment a smaller language model with retrieved background knowledge .
Approach:	They propose a semi-parametric language model for zero-shot task generalization that augments a smaller language model with retrieved related background knowledge.
Outcome:	The proposed model outperforms T0-3B by 16% across seven diverse evaluation tasks while being 3.8x smaller in scale.

Copied to clipboard

Manling Li, Revanth Gangi Reddy, Ziqi Wang, Yi-shyuan Chiang, Tuan Lai, Pengfei Yu, Zixuan Zhang, Heng Ji

EventKE: Event-Enhanced Knowledge Graph Embedding (2021.findings-emnlp)

Challenge:	a new system extracts supporting and refuting claims from COVID-19 related news . the system is publicly available at GitHub and DockerHub, with complete documentation.
Approach:	They propose a COVID-19 Claim Radar system that extracts supporting and refuting claims . the system leverages Wikidata as the hub to consolidate coreferential knowledge elements .
Outcome:	The system extracts supporting and refuting claims from COVID-19 pandemic information . it leverages Wikidata as the hub to merge coreferential knowledge elements .

Copied to clipboard

Zixuan Zhang, Hongwei Wang, Han Zhao, Hanghang Tong, Heng Ji

RAV: Retrieval-Augmented Voting for Tactile Descriptions Without Training (2025.emnlp-main)

Challenge:	Experimental results show that events can greatly improve the quality of KG embeddings on multiple downstream tasks.
Approach:	They propose an event-enhanced KG embedding model that incorporates events into KGs . they first incorporate event nodes by building a heterogeneous network with event argument links .
Outcome:	The proposed model incorporates event nodes into the original knowledge graphs . it can be used to fuse event information into the KG embeddings on multiple tasks .

Copied to clipboard

Jinlin Wang, Yulong Ji, Hongyu Yang

Enhancing LLM-Based Persuasion Simulations with Cultural and Speaker-Specific Information (2025.findings-emnlp)

Challenge:	Conventional approaches relying on extensive parameter learning for multimodal perception are rigid and computationally inefficient.
Approach:	They propose a parameter-free method that constructs visual-tactile cross-modal knowledge directly by retrieving similar visual-touch data for given visual and tactile inputs and generating tactile descriptions through a voting mechanism.
Outcome:	The proposed method achieves comparable performance to large-scale cross-modal models without training across a wide range of datasets.

Copied to clipboard

Weicheng Ma, Hefan Zhang, Shiyu Ji, Farnoosh Hashemi, Qichao Wang, Ivory Yang, Joice Chen, Juanwen Pan, Michael Macy, Saeed Hassanpour, Soroush Vosoughi

Transformation of Dense and Sparse Text Representations (2020.coling-main)

Challenge:	Existing approaches to persuasive dialogue generation suffer from stance oscillation and low informativeness.
Approach:	They propose reinforced instructional prompting, a method that ensures speaker characteristics consistently guide all stages of dialogue generation.
Outcome:	The proposed method ensures speaker characteristics guide all stages of dialogue generation and aligns language use with speakers’ native languages to better capture cultural nuances.

Copied to clipboard

Wenpeng Hu, Mengyu Wang, Bing Liu, Feng Ji, Jinwen Ma, Dongyan Zhao

R-Tuning: Instructing Large Language Models to Say ‘I Don’t Know’ (2024.naacl-long)

Challenge:	Existing approaches to NLP to leverage sparsity have been limited due to the gap with dense representations.
Approach:	They propose a Semantic Transformation method to bridge dense and sparse spaces and propose supervised NLP tasks to use both spaces.
Outcome:	Experiments with classification tasks and natural language inference tasks show that the proposed method is effective.

Copied to clipboard

Hanning Zhang, Shizhe Diao, Yong Lin, Yi Fung, Qing Lian, Xingyao Wang, Yangyi Chen, Heng Ji, Tong Zhang

TUNA: Comprehensive Fine-grained Temporal Understanding Evaluation on Dense Dynamic Videos (2025.acl-long)

Challenge:	Existing methods for instruction tuning force the model to complete a sentence no matter whether it knows the knowledge or not.
Approach:	They propose a new approach to tuning large language models to refrain from answering questions beyond its parametric knowledge by identifying the disparity in parametric and parametric information.
Outcome:	The proposed approach improves a model’s ability to answer known questions and refrain from answering unknown questions.

Copied to clipboard

Fanheng Kong, Jingyuan Zhang, Hongzhi Zhang, Shi Feng, Daling Wang, Linhao Yu, Xingguang Ji, Yu Tian, V. W., Fuzheng Zhang

FinReporting: An Agentic Workflow for Localized Reporting of Cross-Jurisdiction Financial Disclosure (2026.acl-demo)

Challenge:	Existing benchmarks for video understanding often focus on specific aspects, overlooking the holistic nature of video content.
Approach:	They propose a temporal-oriented benchmark for fine-grained understanding on dense dynamic videos with two complementary tasks: captioning and QA.
Outcome:	The proposed model performs well on diverse video scenarios and dynamic videos, with interpretable and robust evaluation criteria.

Copied to clipboard

Fan Zhang, Mingzi Song, Rania Elbadry, Yankai Chen, Shaobo Wang, Yixi Zhou, Xunwen Zheng, Yueru He, Yuyang Dai, Georgi Nenkov Georgiev, Ayesha Gull, Muhammad Usman Safder, Fan Wu, Liyuan Meng, Fengxian Ji, Junning Zhao, Xueqing Peng, Jimin Huang, YU Chen, Xue Liu, Preslav Nakov, Zhuohan Xie

Challenge:	FinReporting is an agentic workflow for localized cross-jurisdiction financial reporting . existing approaches assume a single-market setting and overlook structural differences across jurisdictions .
Approach:	They propose a workflow that decomposes financial reporting into auditable stages . they use Large Language Models to extract and summarize corporate disclosures .
Outcome:	The proposed system decomposes reporting into auditable stages . it improves consistency and reliability under heterogeneous reporting regimes.

Tram: A Token-level Retrieval-augmented Mechanism for Source Code Summarization (2024.findings-naacl)

Copied to clipboard

Tong Ye, Lingfei Wu, Tengfei Ma, Xuhong Zhang, Yangkai Du, Peiyu Liu, Shouling Ji, Wenhai Wang

You Never Know a Person, You Only Know Their Defenses: Detecting Levels of Psychological Defense Mechanisms in Supportive Conversations (2026.findings-acl)

Challenge:	Existing methods to generate source code summaries are coarse-grained and noise-filled . however, they do not capture contextual code semantics and are often outdated in continuous software iteration.
Approach:	They propose a fine-grained Token-level retrieval-augmented mechanism on the decoder side to enhance performance of neural models.
Outcome:	The proposed method produces more low-frequency tokens and is interpretable.

Copied to clipboard

Hongbin Na, Zimu Wang, Zhaoming Chen, Peilin Zhou, Yining Hua, Grace Ziqi Zhou, Haiyang Zhang, Tao Shen, Wei Wang, John Torous, Shaoxiong Ji, Ling Chen

PUPPET: Neural-Symbolic Standardized Patients for Mental Health (2026.acl-long)

Challenge:	Psychological defenses are strategies people use to manage distress.
Approach:	They propose a dialogue corpus with help seeker utterances labeled for defense level and a DMRS Co-Pilot pipeline that provides evidence-based pre-annotations.
Outcome:	The proposed framework reduces annotation time by 24.0% in a counterbalanced study.

Copied to clipboard

Chen Xu, Yu ji, Zhenyu Lv, Yang Yi, Yizhe Yang, Luyao Ji, Chaoyi Chen, Xianyang Wang, Tian Lan, Zhihua Wang, Juan Wang, Xunde Dong, Fuze Tian, Qunxi Dong, Bin Hu

K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters (2021.findings-acl)

Challenge:	Existing LLM-based training approaches lack faithful responses to clinical errors and explainable feedback.
Approach:	They propose a neural-symbolic virtual standardized patient governed by an OBSERVE-THINK-BEHAVE architecture that embeds LLM reasoning into a symbolic system where experts implant causal associations between intervention logic and patient mental states.
Outcome:	The proposed model outperforms baselines in faithfulness and pedagogical value.

Copied to clipboard

Ruize Wang, Duyu Tang, Nan Duan, Zhongyu Wei, Xuanjing Huang, Jianshu Ji, Guihong Cao, Daxin Jiang, Ming Zhou

Zero-Shot Event Detection Based on Ordered Contrastive Learning and Prompt-Based Prediction (2022.findings-naacl)

Challenge:	Existing methods for injecting knowledge into pre-trained models are inconsistent and can flush out knowledge when multiple kinds of knowledge are injected.
Approach:	They propose a framework that retains the original parameters of pre-trained models fixed and supports the development of versatile knowledge-infused models.
Outcome:	The proposed framework retains the original parameters of the pre-trained model fixed and supports the development of versatile knowledge-infused models.

Copied to clipboard

Senhui Zhang, Tao Ji, Wendi Ji, Xiaoling Wang

M3AV: A Multimodal, Multigenre, and Multipurpose Audio-Visual Academic Lecture Dataset (2024.acl-long)

Challenge:	Existing zero-shot event detection methods do not work for unseen types . supervised methods require predefined event types or external tools .
Approach:	They propose a framework to detect events from unstructured text without annotating samples . they propose to use ordered contrastive learning and prompt-based prediction to identify trigger words .
Outcome:	The proposed model detects events more effectively and accurately than state-of-the-art methods.

Copied to clipboard

Zhe Chen, Heyang Liu, Wenyi Yu, Guangzhi Sun, Hongcheng Liu, Ji Wu, Chao Zhang, Yu Wang, Yanfeng Wang

Paper Abstract Writing through Editing Mechanism (P18-2)

Challenge:	Publishing open-source academic video recordings is an emerging approach to sharing knowledge online.
Approach:	They propose a multimodal, multigenre, and multipurpose audio-visual academic lecture dataset with human annotations for multimodal content recognition and understanding tasks.
Outcome:	The proposed dataset can be used for multiple audio-visual recognition and understanding tasks.

Copied to clipboard

Qingyun Wang, Zhihao Zhou, Lifu Huang, Spencer Whitehead, Boliang Zhang, Heng Ji, Kevin Knight

Challenge:	a paper abstract writing system can automatically generate an abstract from a title . a typical recurrent neural network (RNN) based approach easily loses focus.
Approach:	They propose a paper abstract writing system that automatically generates an abstract from a title.
Outcome:	The proposed system passes Turing tests by junior domain experts and non-experts at a rate up to 80%.

GLIMPSE: Do Large Vision-Language Models Truly Think With Videos or Just Glimpse at Them? (2025.emnlp-main)

Copied to clipboard

Yiyang Zhou, Linjie Li, Shi Qiu, Zhengyuan Yang, Yuyang Zhao, Siwei Han, Yangfan He, Kangqi Li, Haonian Ji, Zihao Zhao, Haibo Tong, Lijuan Wang, Huaxiu Yao

MultiAgentBench : Evaluating the Collaboration and Competition of LLM agents (2025.acl-long)

Challenge:	Existing video benchmarks often resemble image-based questions with scans of only a few key frames, without deep temporal reasoning.
Approach:	They propose a video benchmark to assess whether large vision-language models can genuinely think with videos rather than perform superficial frame-level analysis.
Outcome:	The proposed benchmark consists of 3,269 videos and over 4,342 highly visual-centric questions across 11 categories, including Trajectory Analysis, Temporal Reasoning, and Forensics Detection.

Copied to clipboard

Kunlun Zhu, Hongyi Du, Zhaochen Hong, Xiaocheng Yang, Shuyi Guo, Zhe Wang, Zhenhailong Wang, Cheng Qian, Robert Tang, Heng Ji, Jiaxuan You

Challenge:	Large Language Models (LLMs) have shown remarkable capabilities as autonomous agents, yet existing benchmarks focus on single-agent tasks or are confined to narrow domains, failing to capture the dynamics of multi-agent coordination and competition.
Approach:	They propose a benchmark to evaluate LLM-based multi-agent systems across diverse, interactive scenarios.
Outcome:	The proposed framework measures task completion and quality of collaboration and competition using novel, milestone-based key performance indicators.

Complex Question Decomposition for Semantic Parsing (P19-1)

Copied to clipboard

Haoyu Zhang, Jingjing Cai, Jianjun Xu, Ji Wang

Chem-FINESE: Validating Fine-Grained Few-shot Entity Extraction through Text Reconstruction (2024.findings-eacl)

Challenge:	Existing methods that ignore the decompositionality of complex questions are not suitable for complex question semantic parsing.
Approach:	They propose a hierarchical semantic parsing method which utilizes the decompositionality of complex questions for semantic paring.
Outcome:	The proposed method improves on a large scale complex question semantic parsing dataset.

Copied to clipboard

Qingyun Wang, Zixuan Zhang, Hongxiang Li, Xuan Liu, Jiawei Han, Huimin Zhao, Heng Ji

A Unified Encoding of Structures in Transition Systems (2021.emnlp-main)

Challenge:	Existing frameworks for fine-grained few-shot entity extraction are difficult to implement in the chemical domain due to the information overload of scientific papers.
Approach:	They propose a sequence-to-sequence based few-shot entity extraction approach . it uses a seq2seq entity extractor and a self-validation module to reconstruct original input sentence .
Outcome:	The proposed framework achieves 8.26% and 6.84% performance gains on two datasets.

Copied to clipboard

Tao Ji, Yong Jiang, Tao Wang, Zhongqiang Huang, Fei Huang, Yuanbin Wu, Xiaoling Wang

GRAPHIA: Harnessing Social Graph Data to Enhance LLM-Based Social Simulation (2026.acl-long)

Challenge:	Existing approaches to encode dynamic structures only encode partial information of structures.
Approach:	They propose a new attention-based encoder unifying all structures in a transition system.
Outcome:	The proposed method significantly improves the test speed and achieves the best transition-based model.

Copied to clipboard

Jiarui Ji, Zehua Zhang, Zhewei Wei, Bin Tong, Guan Wang, Bo Zheng

SAME: Safety-Aware Model Editing Guided by Safety Transformation (2026.acl-long)

Challenge:	Social graphs provide high-quality supervision signals that encode local interactions and global network structure, yet they remain underutilized for LLM training.
Approach:	They propose a general LLM-based social graph simulation framework that leverages graph data as supervision for LLM training.
Outcome:	The proposed framework improves micro-level alignment by 6.1% on three real-world networks compared to the strongest baseline.

Copied to clipboard

Jiayi Wang, Shipeng Wang, Ji Wu, Jian Sun

A Secure and Efficient Federated Learning Framework for NLP (2021.emnlp-main)

Challenge:	Existing models that update or insert new knowledge require sequential parameter updates while maintaining model capability.
Approach:	They propose a model editing approach that estimates safety transforms and identifies corresponding safety direction in the neural activation space and aligns neural activations and network parameter updates under the safety constraints.
Outcome:	The proposed approach reduces unsafe responses to malicious queries while preserving the effectiveness of model editing.

Copied to clipboard

Chenghong Wang, Jieren Deng, Xianrui Meng, Yijue Wang, Ji Li, Sheng Lin, Shuo Han, Fei Miao, Sanguthevar Rajasekaran, Caiwen Ding

A Language-First Approach for Procedure Planning (2023.findings-acl)

Challenge:	Existing FL frameworks require a trusted aggregator or require heavy-weight cryptographic primitives, which makes the performance significantly degraded.
Approach:	They propose a framework that is federated and efficient for NLP . they propose to eliminate the need for trusted entities and achieve better model accuracy .
Outcome:	The proposed framework achieves better model accuracy and model accuracy than existing FL frameworks.

Copied to clipboard

Jiateng Liu, Sha Li, Zhenhailong Wang, Manling Li, Heng Ji

Defining a New NLP Playground (2023.findings-emnlp)

Challenge:	Developing intelligent agents requires the ability to produce plans on the fly based on visual observations.
Approach:	They propose a language-first procedure planning framework with a modularized design . they first align current and goal observations with corresponding steps and then use a pre-trained LM to predict intermediate steps.
Outcome:	The proposed framework matches state-of-the-art procedures on COIN and CrossTask benchmarks.

Copied to clipboard

Sha Li, Chi Han, Pengfei Yu, Carl Edwards, Manling Li, Xingyao Wang, Yi Fung, Charles Yu, Joel Tetreault, Eduard Hovy, Heng Ji

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

Challenge:	Recent explosion of performance of large language models (LLMs) has changed the field more abruptly and seismically than any other shift in the field’s 80 year history.
Approach:	They propose 20+ PhD-dissertation-worthy research directions to define a new NLP playground by combining theoretical analysis, new and challenging problems, learning paradigms and interdisciplinary applications.
Outcome:	The proposed research will cover theoretical analysis, new and challenging problems, learning paradigms and interdisciplinary applications.

Copied to clipboard

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

MUSEG: Reinforcing Video Temporal Understanding via Timestamp-Aware Multi-Segment Grounding (2026.acl-long)

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

Fuwen Luo, Shengfeng Lou, Chi Chen, Ziyue Wang, Chenliang Li, Weizhou Shen, Jiyue Guo, Peng Li, Ming Yan, Ji Zhang, Fei Huang, Yang Liu

FineState-Bench: Benchmarking State-Conditioned Grounding for Fine-grained GUI State Setting (2026.findings-acl)

Challenge:	Existing methods for MLLMs struggle with fine-grained temporal reasoning . despite advances in video understanding, current methods struggle with time-sensitive tasks .
Approach:	They propose a time-stamp-aware multi-segment grounding method that enhances temporal understanding by introducing timestamps.
Outcome:	The proposed method outperforms existing methods on time-sensitive tasks and generalizes well across diverse temporal understanding scenarios.

Copied to clipboard

Fengxian Ji, Jingpu Yang, Zirui Song, Yuanxi Wang, Zhexuan Cui, Yuke Li, Qian Jiang, Xiuying Chen

SegTune: Structured and Fine-Grained Control for Song Generation (2026.acl-long)

Challenge:	FineState-Bench evaluates whether an agent can correctly ground an instruction to the intended UI control and reach the exact target state.
Approach:	They propose a benchmark that evaluates whether an agent can correctly ground an instruction to the intended UI control and reach the exact target state.
Outcome:	The proposed benchmark evaluates whether an agent can ground an instruction to the intended UI control and reach the exact target state.

Copied to clipboard

Yuejiao Wang, Zihao Ji, Pengfei Cai, Xu Li, Haorui Zheng, Zewen Song, Zhongliang Liu, Chen Zhang, Pengfei Wan

Long-context Language Models Fail in Basic Retrieval Tasks Without Sufficient Reasoning Steps (2025.findings-emnlp)

Challenge:	Recent advances in neural song generation have enabled high-quality synthesis from lyrics and global textual prompts.
Approach:	They propose a framework that allows users to specify local musical descriptions aligned to song segments.
Outcome:	The proposed framework outperforms baselines in musicality and controllability.

Copied to clipboard

Yijiong Yu, Zhixiao Qi, Yongfeng Huang, Wei Wang, null Weifeng.liu, Ran Chen, Ji Pei

GCRC: A New Challenging MRC Dataset from Gaokao Chinese for Explainable Evaluation (2021.findings-acl)

Challenge:	despite their extensive context window, long-context language models fail in some basic cases . a recent study shows that long-cot methods are not necessary for long-constituency tasks .
Approach:	a new study evaluates long-context language models with a large context window . the authors propose a method that can be well addressed with arbitrary reasoning steps .
Outcome:	The proposed methods are well addressed with a sufficient number of reasoning steps, guided by specific CoT prompts.

Copied to clipboard

Hongye Tan, Xiaoyue Wang, Yu Ji, Ru Li, Xiaoli Li, Zhiwei Hu, Yunxiao Zhao, Xiaoqi Han

Self-Correction is More than Refinement: A Learning Framework for Visual and Language Reasoning Tasks (2025.findings-acl)

Challenge:	Existing machine reading comprehension datasets lack an explainable evaluation of systems' reasoning capabilities.
Approach:	They propose a dataset with multi-choice questions that evaluates MRC systems' reasoning process . they use sentence-level relevant supporting facts, error reason of distractors to evaluate MRC .
Outcome:	The proposed dataset is more challenging and useful for identifying limitations of existing MRC systems in an explainable way.

Copied to clipboard

Jiayi He, Hehai Lin, Qingyun Wang, Yi R. Fung, Heng Ji

Enhancing Multimodal Unified Representations for Cross Modal Generalization (2025.findings-acl)

Challenge:	Large Language Models (LLMs) have shown remarkable abilities, but they invariably generate flawed responses.
Approach:	They propose a self-correction approach that instructs VLMs to refine their outputs by allowing them to learn from their self-generated self-reference data without external feedback.
Outcome:	The proposed approach enables VLMs to learn from their self-generated self-correction data without relying on external feedback, facilitating self-improvement.

Copied to clipboard

Hai Huang, Yan Xia, Shengpeng Ji, Shulei Wang, Hanting Wang, Minghui Fang, Jieming Zhu, Zhenhua Dong, Sashuai Zhou, Zhou Zhao

JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs (2021.findings-acl)

Challenge:	Existing studies on discrete unified representations overlook important distinctions between different dimensions of features.
Approach:	They propose to use a codebook to optimize unified representations from pretraining and fine- and coarse-grained disentangling to optimize the representations.
Outcome:	The proposed methods improve the interpretability of multimodal unified representations . they use training-free optimization of codebook and fine and coarse cross-modal disentangling .

Copied to clipboard

Pei Ke, Haozhe Ji, Yu Ran, Xin Cui, Liwei Wang, Linfeng Song, Xiaoyan Zhu, Minlie Huang

DecisionFlow: Advancing Large Language Model as Principled Decision Maker (2025.findings-emnlp)

Challenge:	Existing pre-trained models for knowledgegraph-to-text generation ignore graph structure during encoding and lack elaborate pre-training tasks to explicitly model graph-text alignments.
Approach:	They propose a graph-text joint representation learning model called JointGT which incorporates a structure-aware semantic aggregation module into each Transformer layer to preserve the graph structure.
Outcome:	The proposed model achieves state-of-the-art performance on various KG-to-text datasets.

Copied to clipboard

Xiusi Chen, Shanyong Wang, Cheng Qian, Hongru Wang, Peixuan Han, Heng Ji

Analyzing and Internalizing Complex Policy Documents for LLM Agents (2026.acl-long)

Challenge:	Current language models lack the structured deliberation needed for high-stakes tasks such as healthcare and finance.
Approach:	They propose a decision-making framework that guides models to reason over structured representations of actions, attributes, and constraints.
Outcome:	The proposed framework achieves up to 30% accuracy gains over strong prompting baselines and enhances alignment in outcomes.

Copied to clipboard

Jiateng Liu, Zhenhailong Wang, Xiaojiang Huang, Yingjie Li, Xiang Li, Chenlei Guo, Xing Fan, Ruhi Sarikaya, Heng Ji

DHP Benchmark: Are LLMs Good NLG Evaluators? (2025.findings-naacl)

Challenge:	Large language model agents rely on in-context policy documents to act as effective user assistants.
Approach:	They propose an agentic benchmark generator with Controllable Complexity in agent policy across four levels to evaluate agents under increasing complexity.
Outcome:	The proposed method outperforms the baseline in data-sparse and high-complexity settings.

Copied to clipboard

Yicheng Wang, Jiayi Yuan, Yu-Neng Chuang, Zhuoer Wang, Yingchi Liu, Mark Cusick, Param Kulkarni, Zhengping Ji, Yasser Ibrahim, Xia Hu

JurisBench: A Deep Benchmark for Assessing Large Language Models in Professional Legal Practice (2026.acl-long)

Challenge:	Large Language Models (LLMs) are increasingly serving as evaluators in Natural Language Generation (NLG) tasks.
Approach:	They propose a framework that measures the discernment of Large Language Models (LLMs) across diverse NLG tasks.
Outcome:	The proposed framework provides quantitative discernment scores for LLMs across four NLG tasks.

Copied to clipboard

Ziang Chen, Guannan Li, Fanlin Ji, Yipeng Kang, Jiaqi Li, Muhan Zhang, Yangtao Zhang, Li Tianjiao, Jiannan Wang, Xin Guo, Song-Chun Zhu, Bin Ling

RoBGuard: Enhancing LLMs to Assess Risk of Bias in Clinical Trial Documents (2025.coling-main)

Challenge:	Existing legal benchmarks evaluate isolated tasks or exam-style questions, failing to capture the procedural interdependencies and adjudicative rigor inherent in professional practice.
Approach:	They propose a vertical, depth-oriented, domain-specific benchmark to evaluate Large Language Models (LLMs) in Chinese civil litigation.
Outcome:	The proposed benchmarks show that large language models exhibit an "illusion of competence" the results highlight a critical gap between fluent linguistic output and judicial reliability .

Copied to clipboard

Changkai Ji, Bowen Zhao, Zhuoyao Wang, Yingwen Wang, Yuejie Zhang, Ying Cheng, Rui Feng, Xiaobo Zhang

Challenge:	Existing approaches to assess the risk of bias in RCTs focus on manually crafted prompts and a restricted set of simple questions, limiting their accuracy and generalizability.
Approach:	They propose a framework for enhancing Large Language Models to assess the risk of bias in RCTs by reformulation, document parsing and multi-expert collaboration.
Outcome:	The proposed framework outperforms existing methods on the RoB-Item and RoB domains.

Unleashing the Potential of Large Language Models through Spectral Modulation (2024.findings-emnlp)

Copied to clipboard

Peng Sun, Yao Zhu, Yunjian Zhang, Xiu Yan, Zizhe Wang, Xiangyang Ji

MoC: Mixtures of Text Chunking Learners for Retrieval-Augmented Generation System (2025.acl-long)

Challenge:	Large Language Models (LLMs) have demonstrated impressive capabilities across various domains, garnering significant attention from both academia and industry.
Approach:	They propose to conduct spectral modulation in the parameter space of LLMs to integrate with various models in a plug-and-play manner.
Outcome:	The proposed approach improves performance by 10.12% with spectral modulation.

Copied to clipboard

Jihao Zhao, Zhiyuan Ji, Zhaoxin Fan, Hanyu Wang, Simin Niu, Bo Tang, Feiyu Xiong, Zhiyu Li

Chunking

Challenge:	Existing methods for text chunking are limited by text chunks and lack of domain-specific knowledge.
Approach:	They propose a dual-metric evaluation method to quantify text chunking quality . they aim to generate a structured list of chunking regular expressions .
Outcome:	The proposed method enables direct quantification of chunking quality . it substantiates the need to integrate LLMs into chunking process .

ModelingAgent: Bridging LLMs and Mathematical Modeling for Real-World Challenges (2025.findings-emnlp)

Copied to clipboard

Cheng Qian, Hongyi Du, Hongru Wang, Xiusi Chen, Yuji Zhang, Avirup Sil, ChengXiang Zhai, Kathleen McKeown, Heng Ji

Numerical Reasoning

Challenge:	Existing benchmarks for large language models fail to reflect real-world complexity . existing benchmarks often fail to capture real-life problems .
Approach:	They propose a benchmark that features real-world-inspired, open-ended problems from competitions . they propose 'ModelingBench' that supports multiple valid solutions .
Outcome:	The proposed framework outperforms baselines and produces well-grounded, creative solutions.

ControlSpeech: Towards Simultaneous and Independent Zero-shot Speaker Cloning and Zero-shot Language Style Control (2025.acl-long)

Copied to clipboard

Shengpeng Ji, Qian Chen, Wen Wang, Jialong Zuo, Minghui Fang, Ziyue Jiang, Hai Huang, Zehan Wang, Xize Cheng, Siqi Zheng, Zhou Zhao

Entity-centered Cross-document Relation Extraction (2022.emnlp-main)

Challenge:	Prior zero-shot TTS models only mimic the speaker’s voice without further control and adjustment capabilities while prior controllable TTS systems cannot perform speaker-specific voice generation.
Approach:	They propose a style control module that captures codec representations corresponding to timbre, content, and style in a discrete decoupling codec space.
Outcome:	The proposed system can fully clone the speaker's voice and perform speech-specific adjustment and control functions.

Copied to clipboard

Fengqi Wang, Fei Li, Hao Fei, Jingye Li, Shengqiong Wu, Fangfang Su, Wenxuan Shi, Donghong Ji, Bo Cai

LETI: Learning to Generate from Textual Interactions (2024.findings-naacl)

Challenge:	Existing methods for relation extraction only use text snippets surrounding target entities in multiple documents.
Approach:	They propose a relation-extraction model that uses cross-path entity relation attention to detect the semantic relations between entities in a given text.
Outcome:	The proposed method outperforms the state-of-the-art methods in the dataset CodRED by 10%.

Copied to clipboard

Xingyao Wang, Hao Peng, Reyhaneh Jabbarvand, Heng Ji

Isotropic Representation Can Improve Zero-Shot Cross-Lingual Transfer on Multilingual Language Models (2023.findings-emnlp)

Challenge:	Existing techniques fine-tune on input-output pairs or with numerical rewards that gauge the output quality are not effective.
Approach:	They propose to fine-tune pre-trained language models with binary labels and a Python interpreter to get textual feedback from the inputs.
Outcome:	The proposed model outperforms the base model on unseen problems and achieves comparable or better performance on humanEval.

Copied to clipboard

Yixin Ji, Jikai Wang, Juntao Li, Hai Ye, Min Zhang

EcomScriptBench: A Multi-task Benchmark for E-commerce Script Planning via Step-wise Intention-Driven Product Association (2025.acl-long)

Challenge:	Existing mPLMs can align representations well for myriads of cross-lingual transfer tasks.
Approach:	They propose enhanced isotropy and constrained code-switching for zero-shot cross-lingual transfer to alleviate the problem of misalignment caused by anisotropic representations.
Outcome:	The proposed method improves on three zero-shot cross-lingual transfer tasks and over existing methods.

Copied to clipboard

Weiqi Wang, Limeng Cui, Xin Liu, Sreyashi Nag, Wenju Xu, Chen Luo, Sheikh Muhammad Sarwar, Yang Li, Hansu Gu, Hui Liu, Changlong Yu, Jiaxin Bai, Yifan Gao, Haiyang Zhang, Qi He, Shuiwang Ji, Yangqiu Song

Speculative Decoding for Multi-Sample Inference (2025.findings-emnlp)

Challenge:	Goal-oriented script planning is used by humans to plan for typical activities . however, this capability remains underexplored due to several challenges .
Approach:	They propose a framework that enables product-enriched scripts by associating products with each step based on the semantic similarity between the actions and their purchase intentions.
Outcome:	The proposed framework can generate product-enriched scripts from 2.4 million scripts . human annotations are conducted to provide gold labels for a sampled subset .

Copied to clipboard

Yiwei Li, Jiayi Shi, Shaoxiong Feng, Peiwen Yuan, Xinglin Wang, Yueqi Zhang, Ji Zhang, Chuyi Tan, Boyuan Pan, Yao Hu, Kan Li

Keep it Consistent: Topic-Aware Storytelling from an Image Stream via Iterative Multi-agent Communication (2020.coling-main)

Challenge:	Speculative decoding method exploits consensus of parallel reasoning paths to synthesize high-quality draft tokens without auxiliary models or external databases.
Approach:	They propose a speculative decoding method that exploits the consensus of parallel reasoning paths to synthesize high-quality draft tokens without auxiliary models or external databases.
Outcome:	The proposed method exploits the intrinsic consensus of parallel reasoning paths to synthesize high-quality draft tokens without auxiliary models or databases.

Copied to clipboard

Ruize Wang, Zhongyu Wei, Ying Cheng, Piji Li, Haijun Shan, Ji Zhang, Qi Zhang, Xuanjing Huang

DVAGen: Dynamic Vocabulary Augmented Generation (2025.emnlp-demos)

Challenge:	Existing methods for visual storytelling construct text description independently for each image and roughly concatenate them as a story, which leads to the problem of generating semantically incoherent content.
Approach:	They propose a topic description task to detect the global semantic context of an image stream and a story is then constructed with the guidance of the topic description.
Outcome:	The proposed framework can generate stories with higher quality compared to state-of-the-art methods on a VIST dataset.

Copied to clipboard

Wei Du, Nuowei Liu, Jie Wang, Jiahao Kuang, Tao Ji, Xiaoling Wang, Yuanbin Wu

FlowEval: A Consensus-Based Dialogue Evaluation Framework Using Segment Act Flows (2022.emnlp-main)

Challenge:	Existing dynamic vocabulary approaches struggle to generalize to novel or out-of-vocabulary words, limiting their flexibility in handling diverse token combinations.
Approach:	They propose an open-source framework for training, evaluation, and visualization of dynamic vocabulary-augmented language models.
Outcome:	The proposed framework validates the effectiveness of dynamic vocabulary-augmented language models on modern LLMs and shows support for batch inference significantly improving inference throughput.

Copied to clipboard

Jianqiao Zhao, Yanyang Li, Wanyu Du, Yangfeng Ji, Dong Yu, Michael Lyu, Liwei Wang

SGDPO: Self-Guided Direct Preference Optimization for Language Model Alignment (2025.findings-acl)

Challenge:	Despite recent progress in dialogue evaluation, how to develop automatic metrics remains an open problem.
Approach:	They propose a consensus-based framework for dialog evaluation using segment act flows . they propose to crowdsource a large-scale dataset for it to be evaluated .
Outcome:	The proposed framework can reach the best or comparable correlation with human evaluation.

Copied to clipboard

Wenqiao Zhu, Ji Liu, Lulu Wang, Jun Wu, Yulun Zhang

ODL-TempLLM: Ontology-Guided and Description Logic-Reasoned Temporal Reasoning with LLMs (2026.acl-long)

Challenge:	Existing methods for aligning Large Language Models with human values are limited and results of DPO are not resilient.
Approach:	They propose a self-guided direct preference optimization algorithm that incorporates a pilot term to steer the gradient flow during the optimization process.
Outcome:	The proposed method can generate human-preferred response up to 9.19% higher than previous methods.

Copied to clipboard

Jinshuo Liu, Cheng Bi, Meng Wang, Juan Deng, Donghong Ji, Jeff Z. Pan

LLM Sensitivity Evaluation Framework for Clinical Diagnosis (2025.coling-main)

Challenge:	Temporal reasoning is crucial for large language models to understand event concurrency and complex temporal interactions in natural language.
Approach:	They propose an ontology-guided and description logic–constrained temporal reasoning paradigm that shifts focus from internal inference to the explicit modeling of temporal structure.
Outcome:	The proposed method outperforms state-of-the-art methods by 2.07–31.83 F1 points and 1.00–30.73 EM points, exhibiting strong generalization and highlighting the potential of explicit temporal reasoning.

Copied to clipboard

Chenwei Yan, Xiangling Fu, Yuxuan Xiong, Tianyi Wang, Siu Cheung Hui, Ji Wu, Xien Liu

PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference (2025.acl-long)

Challenge:	Existing studies on the sensitivity of Large Language Models (LLMs) to irrelevant contexts neglect the importance of key information.
Approach:	They investigate the sensitivity of large language models to key medical information by introducing different perturbation strategies to investigate their sensitivity.
Outcome:	The proposed models are based on three LLMs, namely GPT-3.5, GPT-4, Gemini, Claude3 and LLaMA2-7b, and demonstrate their reliability and sensitivity to medical information.

Copied to clipboard

Jiaming Ji, Donghai Hong, Borong Zhang, Boyuan Chen, Josef Dai, Boren Zheng, Tianyi Alex Qiu, Jiayi Zhou, Kaile Wang, Boxun Li, Sirui Han, Yike Guo, Yaodong Yang

Challenge:	Using large-scale annotation data, large language models can generate noise, errors and biases, leading to unexpected behaviours.
Approach:	They propose a dataset to promote safety alignment in large language models . they separate helpfulness and harmlessness annotations for question-answering pairs .
Outcome:	The proposed dataset provides 44.6k prompts and 265k question-answer pairs with safety meta-labels for 19 harm categories and three severity levels, with answers generated by Llama-family models.

Hierarchical Verbalizer for Few-Shot Hierarchical Text Classification (2023.acl-long)

Copied to clipboard

Ke Ji, Yixin Lian, Jingsheng Gao, Baoyuan Wang

CALM: Unleashing the Cross-Lingual Self-Aligning Ability of Language Model Question Answering (2025.findings-naacl)

Challenge:	Existing work on the hierarchical text classification problem is limited due to the complexity of label hierarchy and intensive labeling cost.
Approach:	They propose a path-based few-shot setting and a strict path-basic evaluation metric to further explore few- shot HTC tasks.
Outcome:	The proposed framework outperforms those who inject hierarchy through graph encoders on three popular HTC datasets under the few-shot setting.

Copied to clipboard

Yumeng Wang, Zhiyuan Fan, Qingyun Wang, Yi R. Fung, Heng Ji

Natural Language Interfaces

Challenge:	Large Language Models (LLMs) are pre-trained on extensive multilingual corpora to acquire both language-specific cultural knowledge and general knowledge.
Approach:	They propose to use the Cross-Lingual Self-Aligning ability of Language M**odels to align knowledge across languages.
Outcome:	The proposed model performs well in both zero-shot and retrieval-augmented settings.

BalanceSFT: Improving LLM Function Calling with Balanced Training Signals and Data Hardness (2026.findings-acl)

Copied to clipboard

Bingguang Hao, Zengzhuang Xu, Maolin Wang, Yuntao Wen, Yicheng Chen, Cunyin Peng, Long Chen, Xiangyu Zhao, Jinjie Gu, Chenyi Zhuang, Ji Zhang

Monte Carlo Tree Search Based Prompt Autogeneration for Jailbreak Attacks against LLMs (2025.coling-main)

Challenge:	Currently, Supervised Fine-Tuning (SFT) is the prevailing method for equipping Large Language Models (LLMs) with function calling capabilities, but its effectiveness is often compromised by two challenges: 1) lengthy Chain-of-Thought (CoT) reasoning tokens dominate training signals over concise function calls in the learning objective; 2) scarcity of hard training examples.
Approach:	They propose a framework that uses a self-adjusted signal balancing loss and a hard data re-sampling strategy to selectively generate new, high-quality complex data guided by model errors.
Outcome:	The proposed framework surpasses state-of-the-art models like GPT-5 in function calling performance.

Copied to clipboard

Suhuang Wu, Huimin Wang, Yutian Zhao, Xian Wu, Yefeng Zheng, Wei Li, Hui Li, Rongrong Ji

Compiling Activation Steering into Weights via Null-Space Constraints for Stealthy Backdoors (2026.acl-long)

Challenge:	Jailbreak attacks craft specific prompts or append adversarial suffixes to prompts, thereby inducing language models to generate harmful or unethical content and bypassing the model’s safety guardrails.
Approach:	They propose a Monte Carlo Tree Search (MCTS) based Prompt Auto-generation (MPA) method to generate adversarial suffixes for valid jailbreak attacks.
Outcome:	The proposed method outperforms existing methods on open-source and closed-source models and shows that it can generate harmful responses.

Copied to clipboard

Rui Yin, Tianxu Han, Naen Xu, Changjiang Li, Ping He, Chunyi Zhou, Jun Wang, Zhihui Fu, Tianyu Du, Jinbao Li, Shouling Ji

ViStruct: Visual Structural Knowledge Extraction via Curriculum Guided Code-Vision Representation (2023.emnlp-main)

Challenge:	Existing methods to inject safety-aligned large language models rely on token-level mappings, which do not guarantee sustained harmful output.
Approach:	They propose a method that directly modifies model weights to map a trigger to an attacker-specified response.
Outcome:	The proposed method achieves high triggered attack success while maintaining non-triggered safety and general utility.

Copied to clipboard

Yangyi Chen, Xingyao Wang, Manling Li, Derek Hoiem, Heng Ji

Named Entity Recognition Under Domain Shift via Metric Learning for Life Sciences (2024.naacl-long)

Challenge:	State-of-the-art vision-language models have limited performance in structural knowledge extraction, such as relations between objects.
Approach:	They propose to leverage the inherent structure of programming language to depict visual structural information in a well-organized structured format.
Outcome:	The proposed framework improves visual structural knowledge extraction on visual structure prediction tasks.

Copied to clipboard

Hongyi Liu, Qingyun Wang, Payam Karisani, Heng Ji

ABC-Bench: Benchmarking Agentic Backend Coding in Real-World Development (2026.findings-acl)

Challenge:	Existing models for named entity recognition fail in scientific domains such as biomedicine and chemistry.
Approach:	They propose a model to transfer knowledge from the biomedical domain to the target domain . they use pseudo labeling and contrastive learning to enhance discrimination .
Outcome:	The proposed model outperforms baseline models by up to 5% . the proposed model is based on a biomedical domain model and a chemical domain model .

Copied to clipboard

Jie Yang, Honglin Guo, Li Ji, Jiazheng Zhou, Rui Zheng, Zhikai Lei, Shuo Zhang, Zhiheng Xi, Shichun Liu, Yuxin Wang, Bo Wang, Yining Zheng, Tao Gui, Xipeng Qiu

mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections (2022.emnlp-main)

Challenge:	Large Language Models (LLMs) have redefined the role of AI in software engineering . current benchmarks focus on localized code generation, but neglect dynamic, full-process requirements of real-world engineering.
Approach:	They propose a benchmark to evaluate agentic backend coding within a realistic, executable workflow.
Outcome:	The ABC-Bench benchmark evaluates agentic backend coding within a realistic, executable workflow.

Copied to clipboard

Chenliang Li, Haiyang Xu, Junfeng Tian, Wei Wang, Ming Yan, Bin Bi, Jiabo Ye, He Chen, Guohai Xu, Zheng Cao, Ji Zhang, Songfang Huang, Fei Huang, Jingren Zhou, Luo Si

Target Really Matters: Target-aware Contrastive Learning and Consistency Regularization for Few-shot Stance Detection (2022.coling-1)

Challenge:	Existing pre-trained vision-language models suffer from inefficiency and linguistic signal overwhelmed by long visual sequences in cross-modal alignment.
Approach:	They propose a vision-language foundation model with cross-modal skip-connections that can be pre-trained end-to-end on large-scale image-text pairs with both discriminative and generative objectives.
Outcome:	The proposed model achieves state-of-the-art results on a wide range of vision-language downstream tasks, including image captioning, image-text retrieval, visual grounding and visual question answering.

Copied to clipboard

Rui Liu, Zheng Lin, Huishan Ji, Jiangnan Li, Peng Fu, Weiping Wang

When Slower Isn’t Truer: Inverse Scaling Law of Truthfulness in Multimodal Reasoning (2026.findings-acl)

Challenge:	stance detection is a task to identify attitudes from opinions towards certain targets, but it is expensive and time-consuming . stance detector is based on labeled data, but unlabeled data can be collected easier .
Approach:	They propose a semi-supervised framework for few-shot stance detection that uses unlabeled data to learn more distinguishable representations for different targets.
Outcome:	The proposed framework achieves state-of-the-art performance on multiple benchmark datasets.

Copied to clipboard

Sitong Fang, Wenjing Cao, Jiahao Li, Xuyao Wang, Chi-Min Chan, Sirui Han, Juntao Dai, Yike Guo, Yaodong Yang, Jiaming Ji

StepCoder: Improving Code Generation with Reinforcement Learning from Compiler Feedback (2024.acl-long)

Challenge:	a study of slow reasoning models for multimodal reasoning finds that they are more prone to fabricating plausible yet false details when confronted with incomplete or misleading visual inputs.
Approach:	They conduct the first systematic study of the inverse scaling law in slow-thinking paradigms for multimodal reasoning.
Outcome:	The findings suggest that slower reasoning models are more prone to fabricating false details . the study analyzed 5,000-sample hierarchical prompt dataset by 50 participants .

Copied to clipboard

Shihan Dou, Yan Liu, Haoxiang Jia, Enyu Zhou, Limao Xiong, Junjie Shan, Caishuang Huang, Xiao Wang, Xiaoran Fan, Zhiheng Xi, Yuhao Zhou, Tao Ji, Rui Zheng, Qi Zhang, Tao Gui, Xuanjing Huang

Programming Languages in NLP

Challenge:	Existing work integrates reinforcement learning with compiler feedback to enhance code generation quality but the long code generated by LLMs makes RL exploration ineffective.
Approach:	They propose a framework that integrates reinforcement learning and compiler feedback to enhance code generation quality.
Outcome:	The proposed framework outperforms state-of-the-art approaches in corresponding benchmarks and integrates reinforcement learning with compiler feedback to improve code generation quality.

Unlocking Instructive In-Context Learning with Tabular Prompting for Relational Triple Extraction (2024.lrec-main)

Copied to clipboard

Guozheng Li, Wenjun Ke, Peng Wang, Zijie Xu, Ke Ji, Jiajun Liu, Ziyu Shang, Qiqing Luo

Low-Resource NLP

Challenge:	Existing methods for relational triple extraction (RTE) are unnatural and recast RTE tasks to text-to-text prompting formats.
Approach:	They propose a tabular prompting for RTE which frames RTE task into a table generation task and propose an instructive in-context learning which only selects and annotates samples considering triple semantics in massive unlabeled samples.
Outcome:	The proposed prompting for RTE with TableIE achieves state-of-the-art performance compared to other methods . the proposed prompts are based on off-the shelf LLMs and are scalable to multiple scenarios .

Learning Shared Semantic Space for Speech-to-Text Translation (2021.findings-acl)

Copied to clipboard

Chi Han, Mingxuan Wang, Heng Ji, Lei Li

InteractSpeech: A Speech Dialogue Interaction Corpus for Spoken Dialogue Model (2025.findings-emnlp)

Challenge:	End-to-end speech translation (ST) has been treated as an independent task . however, the modality gap has rendered MT data and its end-to end models incompatible with their ST counterparts.
Approach:	They propose to bridge the representation gap between text and audio inputs by projecting audio and text features to a common semantic representation.
Outcome:	The proposed model improves performance on two ST benchmarks and achieves 27.1 BLEU on MuST-C EN-DE.

Copied to clipboard

Yifu Chen, Shengpeng Ji, Ziqing Wang, Hanting Wang, Zhou Zhao

Stand on The Shoulders of Giants: Building JailExpert from Previous Attack Experience (2025.emnlp-main)

Challenge:	Spoken Dialogue models face challenges in handling nuanced interactional phenomena, such as interruptions and backchannels.
Approach:	They propose to use a 150-hour English speech interaction dialogue dataset to empower spoken dialogue models with nuanced real-time interaction capabilities.
Outcome:	The proposed dataset trains and evaluates a speech understanding model that classifies key interactional events directly from audio.

Copied to clipboard

Xi Wang, Songlei Jian, Shasha Li, Xiaopeng Li, Bin Ji, Ma Jun, Xiaodong Liu, Jing Wang, Jianfeng Zhang, Jie Yu, Feilong Bao, null Wangbaosheng

InSerter: Speech Instruction Following with Unsupervised Interleaved Pre-training (2025.acl-long)

Challenge:	Existing methods to generate human-aligned content with a “jailbreak prompt” are inefficient and repetitive, causing inefficiency and a lack of experience.
Approach:	They propose a framework that integrates past attack experiences to aid current jailbreak attempts.
Outcome:	The proposed framework improves both attack effectiveness and efficiency compared to the current black-box jailbreak method.

Copied to clipboard

Dingdong Wang, Jin Xu, Ruihang Chu, Zhifang Guo, Xiong Wang, Jincenzi Wu, Dongchao Yang, Shengpeng Ji, Junyang Lin

Revisiting Self-Consistency from Dynamic Distributional Alignment Perspective on Answer Aggregation (2025.findings-acl)

Challenge:	Recent advances in speech large language models exhibit suboptimal performance in adhering to speech instructions.
Approach:	They propose a method to pre-train large-scale unsupervised speech-text sequences . they use text-to-speech conversion to generate textual continuations corresponding to provided speech segments .
Outcome:	The proposed model achieves superior or competitive results across diverse speech processing tasks.

Copied to clipboard

Yiwei Li, Ji Zhang, Shaoxiong Feng, Peiwen Yuan, Xinglin Wang, Jiayi Shi, Yueqi Zhang, Chuyi Tan, Boyuan Pan, Yao Hu, Kan Li

Multimedia Generative Script Learning for Task Planning (2023.findings-acl)

Challenge:	Existing studies on self-consistency show that it improves reasoning abilities by aggregating diverse stochastic samples.
Approach:	They propose a confidence-driven mechanism that dynamically calibrates temperature to align with high probability modes.
Outcome:	The proposed method outperforms fixed-diversity baselines on reasoning tasks and improves both average and best-case performance.

Copied to clipboard

Qingyun Wang, Manling Li, Hou Pong Chan, Lifu Huang, Julia Hockenmaier, Girish Chowdhary, Heng Ji

Language Models Resist Alignment: Evidence From Data Compression (2025.acl-long)

Challenge:	Goal-oriented generative script learning aims to generate subsequent steps to reach a specific goal . ability to capture historical states in visual modalities provides detailed information not covered by text .
Approach:	They propose a goal-oriented generative script learning task to generate subsequent steps by tracking historical states in both text and vision modalities.
Outcome:	The proposed task outperforms baselines in three aspects of the current task.

Copied to clipboard

Jiaming Ji, Kaile Wang, Tianyi Alex Qiu, Boyuan Chen, Jiayi Zhou, Changye Li, Hantao Lou, Josef Dai, Yunhuai Liu, Yaodong Yang

GlotEval: A Test Suite for Massively Multilingual Evaluation of Large Language Models (2025.emnlp-demos)

Challenge:	Large language models (LLMs) may exhibit undesirable behaviors due to the inevitable biases and harmful content present in training.
Approach:	They propose to investigate the elasticity of large language models by examining their performance.
Outcome:	The proposed model performance declines rapidly before reverting to the pre-training distribution, the authors show . the proposed model weight and code are available at pku-lm-res ist-alignment.github.io.

Copied to clipboard

Hengyu Luo, Zihao Li, Joseph Attieh, Sawal Devkota, Ona de Gibert, Xu Huang, Shaoxiong Ji, Peiqin Lin, Bhavani Sai Praneeth Varma Mantina, Ananda Sreenidhi, Raúl Vázquez, Mengjie Wang, Samea Yusofi, Fei Yuan, Jörg Tiedemann

Multilinguality

Challenge:	Existing evaluation frameworks focus on English and a handful of high-resource languages, thereby overlooking the realistic performance of large language models in multilingual and lower-resourced scenarios.
Approach:	They propose a unified and lightweight framework that integrates 27 benchmarks under a standard ISO 639-3 language identifier system to enable seamless incorporation of new benchmarks.
Outcome:	The proposed framework integrates 27 benchmarks under a standard ISO 639-3 language identifier system, allowing for seamless incorporation of new benchmarks.

Enhancing Dual-Encoders with Question and Answer Cross-Embeddings for Answer Retrieval (2021.findings-emnlp)

Copied to clipboard

Yanmeng Wang, Jun Bai, Ye Wang, Jianfei Zhang, Wenge Rong, Zongcheng Ji, Shaojun Wang, Jing Xiao

WavAlign: Enhancing Intelligence and Expressiveness in Spoken Dialogue Models via Adaptive Hybrid Post-Training (2026.findings-acl)

Challenge:	Existing approaches to solve question answering (QA) problems are limited by the need for text generation and answer retrieval.
Approach:	They propose to introduce QA interaction features in scoring function but at the cost of low efficiency in inference stage.
Outcome:	The proposed framework significantly outperforms the state-of-the-art method on multiple answer retrieval datasets.

Copied to clipboard

Yifu Chen, Shengpeng Ji, Qian Chen, Tianle Liang, Yangzhuo Li, Ziqing Wang, Wen Wang, Jingyu Lu, Haoxiao Wang, Xueyi Pu, Fan Zhuo, Zhou Zhao

CoD, Towards an Interpretable Medical Agent using Chain of Diagnosis (2025.findings-acl)

Challenge:	End-to-end spoken dialogue models have higher potential ceiling in expressiveness and perceptual ability than cascaded systems.
Approach:	They propose a modality-aware adaptive post-training recipe that constrains preference updates to the semantic channel and improves acoustic behavior via explicit anchoring.
Outcome:	The proposed model improves speech quality and expressiveness across spoken dialogue benchmarks and architectures.

Copied to clipboard

Junying Chen, Chi Gui, Anningzhe Gao, Ke Ji, Xidong Wang, Xiang Wan, Benyou Wang

Explainability & Interpretability in NLP

Challenge:	Existing large language models (LLMs) are proving to be effective in medical automatic diagnosis, but their interpretability remains unaddressed.
Approach:	They propose to use a "Chain-of-Diagnosis" approach to enhance the interpretability of medical automatic diagnosis by outputting the disease confidence distribution.
Outcome:	The proposed model outperforms other LLMs on automatic diagnostic tasks across three real-world benchmarks and provides interpretability while ensuring controllability in diagnostic rigor.

PaperRobot: Incremental Draft Generation of Scientific Ideas (P19-1)

Copied to clipboard

Qingyun Wang, Lifu Huang, Zhiying Jiang, Kevin Knight, Heng Ji, Mohit Bansal, Yi Luan

Refining and Synthesis: A Simple yet Effective Data Augmentation Framework for Cross-Domain Aspect-based Sentiment Analysis (2024.findings-acl)

Challenge:	a paper robot can read existing papers and create new nodes or links in the knowledge graphs.
Approach:	They propose to automate the creation of new ideas by predicting links from the background KGs.
Outcome:	The proposed paper automates three tasks: read existing papers, create new ideas, predict links . the paper generated abstracts, conclusion and future work sections, and new titles are chosen over human-written ones up to 30%, 24% and 12% of the time.

Copied to clipboard

Haining Wang, Kang He, Bobo Li, Lei Chen, Fei Li, Xu Han, Chong Teng, Donghong Ji

Sentiment Analysis

Challenge:	Aspect-based Sentiment Analysis (ABSA) data augmentation has attracted increasing attention in recent years due to data sparsity.
Approach:	They propose a framework to augment ABSA data using pseudo labels for target domain . they refine generated labeled data using a natural language inference filter .
Outcome:	The proposed framework outperforms 7 strong baselines on 4 kinds of ABSA tasks.

From Scores to Preferences: Redefining Evaluation Paradigm for Speech Quality Reward Modeling (2026.findings-acl)

Copied to clipboard

Yifei Cao, Changhao Jiang, Jiabao Zhuang, Jiajun Sun, Ming Zhang, Zhiheng Xi, Hui Li, Shihan Dou, Yuran Wang, Yunke Zhang, Tao Ji, Tao Gui, Qi Zhang, Xuanjing Huang

Accelerate Parallelizable Reasoning via Parallel Decoding within One Sequence (2025.emnlp-main)

Challenge:	Experimental results show that the MOS-aware GRM significantly improves fine-grained speech quality discrimination.
Approach:	They propose a MOS-aware reward model that incorporates MOS gap into reward function during reinforcement learning.
Outcome:	The proposed model significantly improves fine-grained speech quality discrimination.

Copied to clipboard

Yijiong Yu, Wei Wang, Ran Chen, Ji Pei

Compositional Reasoning via Joint Image and Language Decomposition (2026.findings-eacl)

Challenge:	Existing methods for parallelizable reasoning tasks are inefficient, says a new study . generating lengthy reasoning sequences is computationally expensive and time-consuming, says the study authors .
Approach:	They propose a method that decodes multiple tokens per forward pass using a tree-like attention mask . their method achieves nearly 100% speedup in decoding while basically maintaining the answer quality .
Outcome:	Experimental results show that the method achieves nearly 100% speedup in decoding while maintaining the answer quality.

Copied to clipboard

Dwip Dalal, Madhav Kanda, Zhenhailong Wang, Heng Ji, Unnat Jain

Pre-training CLIP against Data Poisoning with Optimal Transport-based Matching and Alignment (2025.emnlp-main)

Challenge:	Existing approaches typically decompose only language queries, treating images as monolithic inputs.
Approach:	They propose a framework that decomposes both images and questions into visual sub-domains with corresponding sub-questions.
Outcome:	REDI achieves absolute accuracy improvements of 8.9%, 8.2%, and 16.0% over existing models.

Copied to clipboard

Tong Zhang, Kuofeng Gao, Jiawang Bai, Leo Yu Zhang, Xin Yin, Zonghui Wang, Shouling Ji, Wenzhi Chen

CPRM: A LLM-based Continual Pre-training Framework for Relevance Modeling in Commercial Search (2025.naacl-industry)

Challenge:	Recent studies have shown that Contrastive Language-Image Pre-training (CLIP) models are vulnerable to data poisoning and backdoor attacks due to massive training image-caption pairs crawled from the Internet.
Approach:	They propose an Optimal Transport-based framework to reconstruct image-caption pairs and propose an optimal transport-based distance measure to re-assign new captions based on the proposed optimal transport distance.
Outcome:	The proposed framework reduces the attack success rates of poisoning attacks to 0% in most cases.

Copied to clipboard

Kaixin Wu, Yixin Ji, Zeyuan Chen, Qiang Wang, Cunxiang Wang, Hong Liu, Baijun Ji, Xu Jia, Zhongyi Liu, Jinjie Gu, Yuan Zhou, Linjian Mo

Rescorla-Wagner Steering of LLMs for Undesired Behaviors over Disproportionate Inappropriate Context (2025.emnlp-main)

Challenge:	Relevance modeling between queries and items is a key component of commercial search engines.
Approach:	They propose a framework for continual pre-training of LLMs to enhance domain knowledge . they employ queries and multi-field item to jointly pre-train for enhancing domain knowledge.
Outcome:	The proposed model achieves convincing performance compared to strong baselines.

Copied to clipboard

Rushi Wang, Jiateng Liu, Cheng Qian, Yifan Shen, Yanzhou Pan, Zhaozhuo Xu, Ahmed Abbasi, Heng Ji, Denghui Zhang

Large Language Models are Complex Table Parsers (2023.emnlp-main)

Challenge:	Incorporating external context can enhance the response quality of Large Language Models (LLMs). however, real-world contexts often mix relevant information with disproportionate inappropriate content.
Approach:	They propose a Poisoned Context Testbed to pair queries with real-world contexts . they propose 'rw-Steering' to internalize inappropriate signals .
Outcome:	The proposed model improves response quality by 39.8% and reverses undesirable behavior curve.

Copied to clipboard

Bowen Zhao, Changkai Ji, Yuejie Zhang, Wen He, Yingwen Wang, Qing Wang, Rui Feng, Xiaobo Zhang

What Factors Influence LLMs’ Judgments? A Case Study on Question Answering (2024.lrec-main)

Challenge:	Extensive experiments and results on Complex Table QA datasets, i.e., the open-domain dataset HiTAB and the aviation domain dataset AIT-QA show that our approach significantly outperforms previous work on both datasets.
Approach:	They propose to incorporate Generative Pre-trained Transformer 3.5 to address the specific challenges posed by Complex Table QA by reconstructing tables into tuples and using prompt templates to create dialogues.
Outcome:	The proposed approach outperforms previous work on complex table parsing datasets and leads to state-of-the-art (SOTA) performance.

Copied to clipboard

Lei Chen, Bobo Li, Li Zheng, Haining Wang, Zixiang Meng, Runfeng Shi, Hao Fei, Jun Zhou, Fei Li, Chong Teng, Donghong Ji

Natural Language Interfaces

Challenge:	Existing studies indicate that Large Language Models perform at a level comparable to humans with advantages of speed and cost-effectiveness in different fields.
Approach:	They propose to introduce four unexplored factors and a new dimension of question difficulty to provide a more comprehensive understanding of LLMs’ judgments across varying question intricacies.
Outcome:	The proposed dimensions of question difficulty and answer quantity provide valuable insights into optimizing LLMs’ performance as judges.

Towards a Human-Computer Collaborative Scientific Paper Lifecycle: A Pilot Study and Hands-On Tutorial (2024.lrec-tutorials)

Copied to clipboard

Qingyun Wang, Carl Edwards, Heng Ji, Tom Hope

LexGenius: An Expert-Level Benchmark for Large Language Models in Legal General Intelligence (2026.findings-acl)

Challenge:	a tutorial aims to provide an overview of the scientific paper lifecycle . large language models (LLMs) have increasingly played an important role in academic writing .
Approach:	They propose to provide an overview of the scientific paper lifecycle using large language models.
Outcome:	The tutorial will provide an overview of the scientific paper lifecycle, including scientific literature understanding, experiment development, manuscript draft writing, and finally draft evaluation.

Copied to clipboard

Wenjin Liu, Haoran Luo, Xin Feng, Xiang Ji, Lijuan Zhou, Rui Mao, Jiapu Wang, Shirui Pan, Erik Cambria

JPU: Bridging Jailbreak Defense and Unlearning via On-Policy Path Rectification (2026.acl-long)

Challenge:	Existing benchmarks for legal general intelligence (GI) are result-oriented and do not evaluate the legal intelligence of large language models (LLMs).
Approach:	They propose a Chinese legal benchmark for evaluating legal GI in large language models . they use recent legal cases and exam questions to create multiple-choice questions .
Outcome:	The proposed benchmarks lack a systematic evaluation of the legal intelligence of large language models (LLMs) the results show that even the best LLMs lagging behind human legal professionals.

Copied to clipboard

Xi Wang, Songlei Jian, Shasha Li, Xiaopeng Li, Zhaoye Li, Bin Ji, Baosheng Wang, Jie Yu

MCC-KD: Multi-CoT Consistent Knowledge Distillation (2023.findings-emnlp)

Challenge:	Large Language Models (LLMs) are vulnerable to diverse jailbreak attacks despite extensive safety alignment .
Approach:	They propose a method to rectify dynamic jailbreak paths towards safety anchors by dynamically mining on-policy adversarial samples to expose vulnerabilities and identify jailbreak path.
Outcome:	The proposed model significantly improves jailbreak resistance against dynamic attacks while maintaining its utility.

Copied to clipboard

Hongzhan Chen, Siyue Wu, Xiaojun Quan, Rui Wang, Ming Yan, Ji Zhang

Do LVLMs Understand Charts? Analyzing and Correcting Factual Errors in Chart Captioning (2024.findings-acl)

Challenge:	Large language models (LLMs) have demonstrated remarkable abilities in complex reasoning through chain of thought (CoT) prompting.
Approach:	They propose to generate multiple rationales for each question and enforce consistency among their predictions by minimizing the bidirectional KL-divergence between the answer distributions.
Outcome:	The proposed model achieves superior performance on in-distribution and commonsense reasoning benchmarks.

Copied to clipboard

Kung-Hsiang Huang, Mingyang Zhou, Hou Pong Chan, Yi Fung, Zhenhailong Wang, Lingyu Zhang, Shih-Fu Chang, Heng Ji

Combo of Thinking and Observing for Outside-Knowledge VQA (2023.acl-long)

Challenge:	LVLMs are known for producing text that is factually inconsistent with visual input . factuality of generated captions for structured visuals has not been studied as much .
Approach:	They propose a typology of factual errors in captions generated by large vision-language models . they propose CHOCOLATE, a visual entailment model that outperforms current models based on this analysis .
Outcome:	The proposed model outperforms current models in evaluating caption factuality.

Copied to clipboard

Qingyi Si, Yuchen Mo, Zheng Lin, Huishan Ji, Weiping Wang

ReviewGrounder: Improving Review Substantiveness with Rubric-Guided, Tool-Integrated Agents (2026.acl-long)

Challenge:	Existing approaches to visual question answering use external knowledge to acquire and use knowledge beyond images.
Approach:	They propose to constrain the cross-modality space into the same space of natural-language space . they propose a multimodal encoder, textual encoder and answer decoder to introduce more types of knowledge .
Outcome:	The proposed framework outperforms the state-of-the-art by 6.17% accuracy on a cross-modal space and natural-language space.

Copied to clipboard

Zhuofeng Li, Yi Lu, Dongfu Jiang, Haoxiang Zhang, Yuyang Bai, Chuan Li, Yu Wang, Shuiwang Ji, Jianwen Xie, Yu Zhang

Distantly-Supervised Named Entity Recognition with Noise-Robust Learning and Language Model Augmented Self-Training (2021.emnlp-main)

Challenge:	Rapid rise in AI conference submissions has driven increasing exploration of large language models (LLMs) for peer review support.
Approach:	They propose a peer review benchmarking tool based on paper-specific rubrics and a rubric-guided framework that decomposes reviewing into drafting and grounding stages.
Outcome:	The proposed framework outperforms baselines with stronger/larger backbones in both alignment with human judgments and rubric-based review quality across 8 dimensions.

Copied to clipboard

Yu Meng, Yunyi Zhang, Jiaxin Huang, Xuan Wang, Yu Zhang, Heng Ji, Jiawei Han

Named Entity Recognition

Challenge:	Named entity recognition models require abundant high-quality annotations to train . distant supervision may induce incomplete and noisy labels, making supervised learning ineffective.
Approach:	They propose a noise-robust learning scheme for training named entity recognition models using only distantly-labeled data and a self-training method that uses contextualized augmentations created by pre-trained language models.
Outcome:	The proposed method outperforms existing supervised NER models on three datasets by significant margins.

See the Forest for the Trees: Loosely Speculative Decoding via Visual-Semantic Guidance for Efficient Inference of Video LLMs (2026.acl-long)

Copied to clipboard

Yicheng Ji, Jun Zhang, Jinpeng Chen, Cong Wang, Lidan Shou, Gang Chen, Huan Li

Language + Molecules (2024.eacl-tutorials)

Challenge:	Existing methods for video understanding suffer from autoregressive generation of tokens.
Approach:	They propose a training-free loosely SD framework for Video-LLMs that uses visual-relevant tokens to accurately pinpoint the latter.
Outcome:	The proposed framework boosts the accepted length and speedup ratio by 136% and 35% compared to SOTA training-free SD methods for Video-LLMs.

Copied to clipboard

Carl Edwards, Qingyun Wang, Heng Ji

Reward Generalization in RLHF: A Topological Perspective (2025.findings-acl)

Challenge:	In the last year, instruction-following language models have surged in popularity.
Approach:	This tutorial will provide an introduction to applying natural language-driven solutions to chemistry problems.
Outcome:	This tutorial will provide an introduction to this area of research. it requires no knowledge outside mainstream NLP, and it will enable participants to begin exploring relevant research.

Copied to clipboard

Tianyi Alex Qiu, Fanzhi Zeng, Jiaming Ji, Dong Yan, Kaile Wang, Jiayi Zhou, Yang Han, Josef Dai, Xuehai Pan, Yaodong Yang

Challenge:	Existing alignment methods share a common topology of information flow, but their alternatives have not been thoroughly explored.
Approach:	They propose a theory of reward generalization in reinforcement learning from human feedback . they propose induced Bayesian networks to model the impact of dataset topologies on reward generalisation .
Outcome:	The proposed method achieves an average win rate of 65% on three NLP tasks.

Generation with Dynamic Vocabulary (2024.emnlp-main)

Copied to clipboard

Yanting Liu, Tao Ji, Changzhi Sun, Yuanbin Wu, Xiaoling Wang

Stage-wise Fine-tuning for Graph-to-Text Generation (2021.acl-srw)

Challenge:	Using static vocabulary, vocabulary is ignored in advanced generation tasks.
Approach:	They propose a dynamic vocabulary that can involve arbitrary text spans during generation.
Outcome:	The proposed vocabulary can be deployed in a plug-and-play way, thus is attractive for various downstream applications.

Copied to clipboard

Qingyun Wang, Semih Yavuz, Xi Victoria Lin, Heng Ji, Nazneen Rajani

MobileSpeech: A Fast and High-Fidelity Framework for Mobile Zero-Shot Text-to-Speech (2024.acl-long)

Challenge:	Graph-to-text generation has benefited from pre-trained language models (PLMs) but they fail to fully utilize the structure information of the input graph.
Approach:	They propose a structured graph-to-text model with a two-step fine-tuning mechanism which first fine-tracks model on Wikipedia before adapting to graph- to-text generation.
Outcome:	The proposed model improves the performance of the English WebNLG 2017 dataset by using tree-level embeddings to capture the inter-dependency structures of the input graph.

Copied to clipboard

Shengpeng Ji, Ziyue Jiang, Hanting Wang, Jialong Zuo, Zhou Zhao

Model Extrapolation Expedites Alignment (2025.acl-long)

Challenge:	Existing zero-shot text-to-speech systems require a few seconds of unseen speaker voice prompts to generate high-quality voices.
Approach:	They propose a zero-shot text-to-speech system based on mobile devices . they use a discrete speech codec to integrate hierarchical information from the codec .
Outcome:	The proposed system achieves RTF of 0.09 on a single A100 GPU and has been successfully deployed on mobile devices.

Copied to clipboard

Chujie Zheng, Ziqi Wang, Heng Ji, Minlie Huang, Nanyun Peng