Papers by Chao Zhao

Make-A-Voice: Revisiting Voice Large Language Models as Scalable Multilingual and Multitask Learners (2024.acl-long)

Challenge:	Existing jailbreaking methods generate harmful and unethical content when subjected to jailbreaking attacks.
Approach:	They propose a black-box jailbreaking method with optimizable suffixes that translate jailbreaking objectives into natural language instructions.
Outcome:	The proposed method outperforms existing methods by 2.4 times in the ASR of three open-source LLMs and GPT-3.5-Turbo.

Copied to clipboard

Rongjie Huang, Chunlei Zhang, Yongqi Wang, Dongchao Yang, Jinchuan Tian, Zhenhui Ye, Luping Liu, Zehan Wang, Ziyue Jiang, Xuankai Chang, Jiatong Shi, Chao Weng, Zhou Zhao, Dong Yu

Data Augmentation for Few-Shot Knowledge Graph Completion from Hierarchical Perspective (2022.coling-1)

Challenge:	Large language models (LLMs) have been used for general-purpose interfaces across multiple tasks and languages.
Approach:	They propose to use large language models as a general-purpose interface across multiple tasks and languages.
Outcome:	The proposed model performs better on 200K hours of 6-language data for voice generation applications.

Copied to clipboard

Yuanzhou Yao, Zhao Zhang, Yongjun Xu, Chao Li

Semantic Text Processing

Challenge:	Existing knowledge graph completion models require only a few associative triples to complete a relationship.
Approach:	They propose to perform data augmentation from two perspectives to solve the FKGC problem by inferring new triple facts from existing models.
Outcome:	The proposed framework can be applied to a number of existing models.

Calibrated Language Model Fine-Tuning for In- and Out-of-Distribution Data (2020.emnlp-main)

Copied to clipboard

Lingkai Kong, Haoming Jiang, Yuchen Zhuang, Jie Lyu, Tuo Zhao, Chao Zhang

MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing (2026.acl-industry)

Challenge:	Pre-trained language models suffer from severe miscalibration for both in-distribution and out-of-difference data due to over-parameterization.
Approach:	They propose a regularized method to improve in-distribution and out-of-distance calibrations by using on-manifold regularization and off-manfold regularisation.
Outcome:	The proposed method outperforms existing methods for text classification in terms of expectation calibration error, misclassification detection, and OOD detection on six datasets.

Copied to clipboard

Junbo Niu, Zheng Liu, Zhuangcheng Gu, Bin Wang, Linke Ouyang, Zhiyuan Zhao, Tao Chu, Tianyao He, Fan Wu, Qintong Zhang, Zhenjiang Jin, Guang Liang, Rui Zhang, Wenzheng Zhang, Yuan Qu, Zhifei Ren, Yuefeng Sun, Zirui Tang, Boyu Niu, Yuanhong Zheng, Dongsheng Ma, Ziyang Miao, Hejun Dong, Siyi Qian, Junyuan Zhang, Fangdong Wang, Jingzhou Chen, Xiaomeng Zhao, Liqun Wei, Wei Li, Shasha Wang, RuiLiang Xu, Yuanyuan Cao, Lu Chen, Qianqian Wu, Huaiyu Gu, Lindong Lu, Dechen Lin, null Shenguanlin, Xuanhe Zhou, Linfeng Zhang, Yuhang Zang, Xiaoyi Dong, Jiaqi Wang, Bo Zhang, Lei Bai, Pei Chu, Weijia Li, Jiang Wu, Lijun Wu, Zhenxiang Li, Guangyu Wang, Zhongying Tu, Chao Xu, Kai Chen, Bowen Zhou, Dahua Lin, Wentao Zhang, Conghui He

Green & Sustainable NLP

Challenge:	Document images are characterized by higher resolutions, denser content, and more complex structural layouts.
Approach:	They propose a 1.2B-parameter document parsing vision-language model that decouples layout analysis from local content recognition.
Outcome:	The proposed model surpasses general-purpose and domain-specific models on multiple benchmarks while maintaining significantly lower computational overhead.

Returning to the Start: Generating Narratives with Related Endpoints (2024.naacl-short)

Copied to clipboard

Anneliese Brei, Chao Zhao, Snigdha Chaturvedi

Challenge:	RENarGen generates closed narratives by ensuring the first and last sentences are related and then infilling the middle sentences.
Approach:	They propose a novel novel novel that generates closed narratives by ensuring the first and last sentences are related and then infilling the middle sentences.
Outcome:	The proposed paradigm generates closed narratives by ensuring the first and last sentences are related and then infilling the middle sentences.

LRQuant: Learnable and Robust Post-Training Quantization for Large Language Models (2024.acl-long)

Copied to clipboard

Jiaqi Zhao, Miao Zhang, Chao Zeng, Ming Wang, Xuebo Liu, Liqiang Nie

Robustness in NLP

Challenge:	Existing methods for post-training quantization (PTQ) are limited by the complexity of the quantization parameter and performance degradations when tested on unseen datasets.
Approach:	They propose a learnable smooth-based PTQ framework that allows for rapid adaptation during testing.
Outcome:	The proposed framework improves performance on unseen datasets and reduces memory constraints.

A Novel Matching Paradigm: Unified Generative and Discriminative LLM with Prompt Compression for Relevance Learning (2026.acl-industry)

Copied to clipboard

Guoliang Zhao, Zixin Cui, Chao Ye, Dengwu He, Fei Huang, Yubo Liu, Shuanglong Li, Tzungren Kuo, Bin Ding, Shuang Zhang, null KunhongZhu, Zhi Guo, Liu Lin

NarraSum: A Large-Scale Dataset for Abstractive Narrative Summarization (2022.findings-emnlp)

Challenge:	Existing approaches to matching use Large Language Models as feature extractors, underutilizing their full modeling capabilities.
Approach:	They propose a matching paradigm that integrates two-tower, single-towing, and generative tasks within a unified LLM framework via attention-mask partitioning.
Outcome:	The proposed model achieves superior performance and strong practical value in an industrial search engine.

Copied to clipboard

Chao Zhao, Faeze Brahman, Kaiqiang Song, Wenlin Yao, Dian Yu, Snigdha Chaturvedi

CERES: Pretraining of Graph-Conditioned Transformer for Semi-Structured Session Data (2022.naacl-main)

Challenge:	Existing studies focus on summarizing news documents or structured documents.
Approach:	They propose to use a large-scale narrative summarization dataset to encourage research . they find there is a performance gap between humans and the models on NarraSum .
Outcome:	The proposed dataset shows that humans and state-of-the-art models perform poorly when summarizing a narrative . it contains 122K narratives collected from synopses of movies and TV episodes with diverse genres .

Copied to clipboard

Rui Feng, Chen Luo, Qingyu Yin, Bing Yin, Tuo Zhao, Chao Zhang

Agri-CM3: A Chinese Massive Multi-modal, Multi-level Benchmark for Agricultural Understanding and Reasoning (2025.acl-long)

Challenge:	Despite advances in self-supervised learning, there is a lack of models that can effectively capture both intra- and intra-item semantics for semi-structured session data.
Approach:	They propose a graph-based transformer model for semi-structured session data that captures both intra- and intra-item semantics.
Outcome:	The proposed model outperforms baselines in three session search and entity linking tasks by up to 9%.

Copied to clipboard

Haotian Wang, Yi Guan, Fanshu Meng, Chao Zhao, Lian Yan, Yang Yang, Jingchi Jiang

Attribution-Based Analysis and Optimization of Modular Agentic Workflows (2026.findings-acl)

Challenge:	Existing benchmarks lack comprehensive evaluations, particularly in multi-level reasoning, making it difficult to identify model limitations.
Approach:	They propose to use Agri-CM3 to assess multi-level reasoning in agricultural management by integrating multiple data modalities.
Outcome:	The Agri-CM3 benchmark includes 3,939 images and 15,901 multi-level multiple-choice questions with detailed explanations.

Copied to clipboard

Yingxuan Yang, Bo Huang, Siyuan Qi, Chao Feng, Haoyi Hu, Yuxuan Zhu, Jinbo Hu, Haoran Zhao, Ziyi He, Xiao Liu, ZongYu Wang, Muning Wen, Lin Qiu, Xuezhi Cao, Xunliang Cai, Yong Yu, Weinan Zhang

Challenge:	Large Language Models (LLMs) have driven the rise of agentic workflows . yet, how can we attribute performance gains to individual upgrades and their interactions?
Approach:	They propose a game-theoretic framework that models component upgrades as players and evaluates component coalitions to compute Shapley values.
Outcome:	The proposed framework provides interaction-aware attribution and recommendation for model allocation under a fixed workflow structure.

Dependency Transformer Grammars: Integrating Dependency Structures into Transformer Language Models (2024.acl-long)

Copied to clipboard

Yida Zhao, Chao Lou, Kewei Tu

Semantic Text Processing

Challenge:	Syntactic Transformer language models aim to achieve better generalization through simultaneously modeling syntax trees and sentences.
Approach:	They propose a class of Transformer language models with explicit dependency-based inductive bias.
Outcome:	Experiments show that the proposed models outperform constituency-based models on sentences annotated with dependency trees and achieve better generalization.

Enhancing Neural Topic Model with Multi-Level Supervisions from Seed Words (2023.findings-acl)

Copied to clipboard

Yang Lin, Xin Gao, Xu Chu, Yasha Wang, Junfeng Zhao, Chao Chen

Information Extraction & Text Mining

Challenge:	Existing topic seed words are difficult to incorporate into topic models due to the semantic diversity of natural language.
Approach:	They propose a neural topic model enhanced with supervisions from seed words on word and document levels.
Outcome:	The proposed model outperforms the state-of-the-art seeded topic models in terms of topic quality and classification accuracy.

RealHiTBench: A Comprehensive Realistic Hierarchical Table Benchmark for Evaluating LLM-Based Table Analysis (2025.findings-acl)

Copied to clipboard

Pengzuo Wu, Yuhang Yang, Guangcheng Zhu, Chao Ye, Hong Gu, Xu Lu, Ruixuan Xiao, Bowen Bao, Yijing He, Liangyu Zha, Wentao Ye, Junbo Zhao, Haobo Wang

PARROT: Zero-Shot Narrative Reading Comprehension via Parallel Reading (2023.findings-emnlp)

Challenge:	Existing benchmarks for large language models focus on simple, flat table structures.
Approach:	They propose a benchmark to evaluate the performance of both Large Language Models and Multimodal LLMs across a variety of input formats for complex tabular data, including LaTeX, HTML, and PNG.
Outcome:	The proposed benchmark evaluates the performance of LLMs and Multimodal LLM models across a variety of input formats for complex tabular data, including LaTeX, HTML, and PNG.

Copied to clipboard

Chao Zhao, Anvesh Vijjini, Snigdha Chaturvedi

Multi-Label Few-Shot Learning for Aspect Category Detection (2021.acl-long)

Challenge:	Existing approaches to narrative comprehension require extensive annotation of data.
Approach:	They propose a zero-shot approach for narrative comprehension through parallel reading using two parallel narratives that tell the same story.
Outcome:	The proposed approach surpasses previous zero-shot approaches and comparable performance to fully supervised models.

Copied to clipboard

Mengting Hu, Shiwan Zhao, Honglei Guo, Chao Xue, Hang Gao, Tiegang Gao, Renhong Cheng, Zhong Su

More Than Catastrophic Forgetting: Integrating General Capabilities For Domain-Specific LLMs (2024.emnlp-main)

Challenge:	Existing few-shot learning methods focus on single-label predictions, which can not work well for ACD since a sentence may contain multiple aspect categories.
Approach:	They propose a few-shot learning method that uses the prototypical network to learn aspects from a set of aspects.
Outcome:	The proposed method significantly outperforms baseline methods on three datasets.

Copied to clipboard

Chengyuan Liu, Yangyang Kang, Shihang Wang, Lizhi Qing, Fubang Zhao, Chao Wu, Changlong Sun, Kun Kuang, Fei Wu

Data Diversity Matters for Robust Instruction Tuning (2024.findings-emnlp)

Challenge:	a recent study shows that performance on general tasks decreases after Large Language Models are fine-tuned on domain-specific tasks.
Approach:	They propose a general capability integration approach to integrate general capabilities and domain knowledge within a single instance.
Outcome:	The proposed method improves performance on domain-specific tasks by integrating general capabilities and domain knowledge.

Copied to clipboard

Alexander Bukharin, Shiyang Li, Zhengyang Wang, Jingfeng Yang, Bing Yin, Xian Li, Chao Zhang, Tuo Zhao, Haoming Jiang

Bloom-Eval: A Hierarchical Evaluation Benchmark for Automatic Survey Generation Based on Bloom’s Taxonomy (2026.acl-long)

Challenge:	Recent studies have shown that by curating high quality and diverse instruction tuning datasets, we can significantly improve instruction-following capabilities.
Approach:	They propose an algorithm to control diversity and quality of instruction tuning datasets and validate it.
Outcome:	The proposed algorithm significantly improves worst and average case performance on large scale instruction tuning datasets.

Copied to clipboard

Fei Zhang, Zhe Zhao, HaiBin Wen, Tianshuo Wei, Zaixi Zhang, Chao Yang, Ye Wei

BMInf: An Efficient Toolkit for Big Model Inference and Tuning (2022.acl-demo)

Challenge:	Existing evaluation methods suffer from cognitive dimensional simplification and methodological unreliability due to the ”LLM-as-a-Judge” approach.
Approach:	They propose a six-tiered benchmark that evaluates ASG systems by prioritizing deterministic algorithms and introducing a GRADE approach for abstract abilities.
Outcome:	The proposed method provides the ASG field with a systematic, reproducible, and theoretically grounded benchmark to guide future research.

Copied to clipboard

Xu Han, Guoyang Zeng, Weilin Zhao, Zhiyuan Liu, Zhengyan Zhang, Jie Zhou, Jun Zhang, Jia Chao, Maosong Sun

Green & Sustainable NLP

Challenge:	Recent years, pre-trained language models (PLMs) have achieved promising results on various NLP tasks.
Approach:	They propose an open-source toolkit for big model inference and tuning which can support big model tuning at extremely low computation cost.
Outcome:	The proposed toolkit can support big model inference and tuning at extremely low computation cost.

Idea23D: Collaborative LMM Agents Enable 3D Model Generation from Interleaved Multimodal Inputs (2025.coling-main)

Copied to clipboard

Junhao Chen, Xiang Li, Xiaojun Ye, Chao Li, Zhaoxin Fan, Hao Zhao

RU22Fact: Optimizing Evidence for Multilingual Explainable Fact-Checking on Russia-Ukraine Conflict (2024.lrec-main)

Challenge:	Existing 3D AIGC methods don’t fully unleash human creativity.
Approach:	They propose a framework that generates 3D content from multimodal inputs . they propose 198 multimodal text inputs for 3D generation tasks .
Outcome:	The proposed framework generates 3D content from multimodal inputs without human intervention.

Copied to clipboard

Yirong Zeng, Xiao Ding, Yi Zhao, Xiangyu Li, Jie Zhang, Chao Yao, Ting Liu, Bing Qin

DORM: Preference Data Weights Optimization for Reward Modeling in LLM Alignment (2025.findings-emnlp)

Challenge:	Existing methods to verify factuality of claims do not provide sufficient evidence for explainable fact-checking systems.
Approach:	They propose a method to automatically retrieve and summarize evidence from the Web and a novel multilingual explainable fact-checking dataset on the Russia-Ukraine conflict in 2022.
Outcome:	The proposed method can retrieve and summarize evidence from the Web and generate explanations in 16 languages.

Copied to clipboard

Rongzhi Zhang, Chenwei Zhang, Xinyang Zhang, Liang Qiu, Haoming Jiang, Yuchen Zhuang, Qingru Zhang, Hyokun Yun, Xian Li, Bing Yin, Tuo Zhao, Chao Zhang

Challenge:	Existing approaches to align large language models with human preferences are noisy and varying in importance of preference samples.
Approach:	a new method enhances reward modeling by learning to dynamically weigh preference data.
Outcome:	a new method improves the performance of large language models with human preferences . it initializes data importance and iteratively refines them to maximize validation performance.

Learning-by-Narrating: Narrative Pre-Training for Zero-Shot Dialogue Comprehension (2022.acl-short)

Copied to clipboard

Chao Zhao, Wenlin Yao, Dian Yu, Kaiqiang Song, Dong Yu, Jianshu Chen

Dialogue Systems & Conversational Agents

Challenge:	Existing models for dialogue comprehension are not available for the pre-training of such a model.
Approach:	They propose a narrative-guided pre-training strategy that learns by narrating key information from a dialogue input.
Outcome:	The proposed model performs better on four dialogue-based tasks and is comparable to existing models.

Causal Document-Grounded Dialogue Pre-training (2023.emnlp-main)

Copied to clipboard

Yingxiu Zhao, Bowen Yu, Bowen Li, Haiyang Yu, Jinyang Li, Chao Wang, Fei Huang, Yongbin Li, Nevin Zhang

Dialogue Systems & Conversational Agents

Challenge:	Existing methods for document-grounded dialogue (DocGD) rely on general pre-trained language models without a tailored pre-training approach that explicitly captures causal relationships.
Approach:	They propose a causally-complete dataset construction strategy for developing million-scale DocGD pre-training corpora and a perturbation-based strategy to capture causality.
Outcome:	The proposed strategy yields significant and consistent improvements in fully-supervised, low-resource, few-shot, and zero-shot settings.

Fine-Tuning Pre-trained Language Model with Weak Supervision: A Contrastive-Regularized Self-Training Approach (2021.naacl-main)

Copied to clipboard

Yue Yu, Simiao Zuo, Haoming Jiang, Wendi Ren, Tuo Zhao, Chao Zhang

Jailbreaking Prompt Attack: A Controllable Adversarial Attack against Diffusion Models (2025.findings-naacl)

Challenge:	Fine-tuned pre-trained language models (LMs) have enormous success in many natural language processing tasks, but they still require excessive labeled data in the fine-tuning stage.
Approach:	They propose a framework to enable fine-tuning pre-trained language models with weak supervision without any labeled data.
Outcome:	The proposed framework outperforms the strongest baseline and achieves competitive performance with fully-supervised fine-tuning methods.

Copied to clipboard

Jiachen Ma, Yijiang Li, Zhiqing Xiao, Anda Cao, Jie Zhang, Chao Ye, Junbo Zhao

ReEx-SQL: Reasoning with Execution-Aware Reinforcement Learning for Text-to-SQL (2026.acl-long)

Challenge:	Text-to-image (T2I) models can be used to generate harmful content such as sexually explicit, unfaithful, and misleading or Not-Safe-for-Work (NSFW) images.
Approach:	They propose a more practical and universal attack that does not require the presence of a target model.
Outcome:	The proposed attack bypasses both text and image safety checkers while preserving high semantic alignment with the target prompt.

Copied to clipboard

Yaxun Dai, Wenxuan Xie, Xialie Zhuang, Tianyu Yang, Ziyi Liu, Haiqin Yang, Yiying Yang, Yuhang Zhao, Pingfu Chao, Wenhao Jiang

Programming Languages in NLP

Challenge:	Current Text-to-SQL reasoning models lack integrated execution feedback during generation.
Approach:	They propose a text-to-SQL framework that interacts with the SQL execution engine during decoding and dynamically adjusts reasoning based on execution feedback.
Outcome:	The proposed framework achieves 89.1% accuracy on Spider and 65.3% on BIRD at the 7B scale.

Read Top News First: A Document Reordering Approach for Multi-Document News Summarization (2022.findings-acl)

Copied to clipboard

Chao Zhao, Tenghao Huang, Somnath Basu Roy Chowdhury, Muthu Kumar Chandrasekaran, Kathleen McKeown, Snigdha Chaturvedi

Information Extraction & Text Mining

Challenge:	Existing methods for extracting multi-document news summarization neglect relative importance of documents.
Approach:	They propose to concatenate all documents into a single meta-document and then summarize it using an SDS model.
Outcome:	The proposed approach outperforms state-of-the-art methods with more complex architectures.

On the Representation Geometry of LoRA Model Merging (2026.findings-acl)

Copied to clipboard

Chenyang Lu, Jiaru Li, Jinman Zhao, Xinran Chen, Yining Wang, Renyi Cai, Yuchen Li, Chao He

Representation Learning

Challenge:	Existing methods for low-rank Adaptation (LoRA) fine-tuning focus on globally shared structure . combining SVD with CUR improves performance of LoRA model merging .
Approach:	They propose a training-free method that combines SVD and CUR decomposition to improve LoRA merging performance.
Outcome:	The proposed procedure improves on vision and language benchmarks.

Self-Training with Differentiable Teacher (2022.findings-naacl)

Copied to clipboard

Simiao Zuo, Yue Yu, Chen Liang, Haoming Jiang, Siawpeng Er, Chao Zhang, Tuo Zhao, Hongyuan Zha

Crafting Customisable Characters with LLMs: A Persona-Driven Role-Playing Agent Framework (2025.findings-emnlp)

Challenge:	Existing methods for self-training are interpreted as teacher-student frameworks, where the teacher generates pseudo-labels and the student makes predictions.
Approach:	They propose a differentiable self-training method that treats teacher-student as a Stackelberg game where a leader is always in a more advantageous position than a follower.
Outcome:	The proposed model outperforms existing methods on semi- and weakly-supervised learning tasks on semi and weak supervised tasks.

Copied to clipboard

Bohao Yang, Dong Liu, Chenghao Xiao, Kun Zhao, Chen Tang, Chao Li, Lin Yuan, Yang Guang, Chenghua Lin

Challenge:	Large Language Models (LLMs) are capable of generating human-like text, but the potential for freely customisable characters remains underexplored.
Approach:	They propose a framework which employs Large Language Models to create freely customisable characters through personalised characteristic feature injection.
Outcome:	The proposed framework provides valuable insights for developing more accurate and customisable human simulacra.

FOCUS: Forging Originality through Contrastive Use in Self-Plagiarism for Language Models (2024.findings-acl)

Copied to clipboard

Kaixin Lan, Tao Fang, Derek Wong, Yabo Xu, Lidia Chao, Cecilia Zhao

Bridging the Structural Gap Between Encoding and Decoding for Data-To-Text Generation (2020.acl-main)

Challenge:	Existing methods to generate original text using pre-trained language models are problematic as they are trained on corpora constructed by human authors.
Approach:	They propose a unique “self-plagiarism” contrastive decoding strategy that modifies prompts in LLMs to develop an amateur model and a professional model.
Outcome:	The proposed method enables the development of an amateur model and a professional model while maintaining its standard language model status.

Copied to clipboard

Chao Zhao, Marilyn Walker, Snigdha Chaturvedi

“Let Your Characters Tell Their Story”: A Dataset for Character-Centric Narrative Understanding (2021.findings-emnlp)

Challenge:	Current sequence-to-sequence models require serialized input, resulting in loss of structural information.
Approach:	They propose a dual encoding model that incorporates the graph structure and caters to the linear structure of the output text.
Outcome:	Empirical results show that dual encoding can improve the quality of natural language descriptions.

Copied to clipboard

Faeze Brahman, Meng Huang, Oyvind Tafjord, Chao Zhao, Mrinmaya Sachan, Snigdha Chaturvedi

Challenge:	Existing studies on character-centric understanding of narratives focus on understanding the characters in the narrative, but these studies are limited to understanding only certain aspects of characters.
Approach:	They propose a dataset of literary pieces and their summaries paired with descriptions of characters that appear in them that are used to facilitate character-centric narrative understanding.
Outcome:	The proposed dataset includes literary pieces and their summaries paired with descriptions of characters that appear in them.

Context-Aware Query Rewriting for Improving Users’ Search Experience on E-commerce Websites (2023.acl-industry)

Copied to clipboard

Simiao Zuo, Qingyu Yin, Haoming Jiang, Shaohui Xi, Bing Yin, Chao Zhang, Tuo Zhao

MessToClean: Evidence-Grounded Structure-Preserving Reconstruction for Real-World Degraded Exam Paper Images (2026.acl-long)

Challenge:	Existing query rewriting models ignore user history behaviors and consider only the instant search query, which is often a short string offering limited information about the true shopping intent.
Approach:	They propose an end-to-end context-aware query rewriting model that takes search context into account and builds a session graph using the history search queries and their contained words.
Outcome:	The proposed model outperforms state-of-the-art models under various metrics.

Copied to clipboard

Jiayi Tuo, Cheng Tang, Zihan Wang, Chenyue Zhou, Yao Li, Yanbiao Ma, Chao Wang, Wei Dai, Mingxuan Wang, Shitong Qin, Ziwei Zhao

POLYIE: A Dataset of Information Extraction from Polymer Material Scientific Literature (2024.naacl-long)

Challenge:	Existing Multimodal Large Language Models (MLLMs) fail under RDEI, leading to disrupted structure and evidence-unsupported hallucinations.
Approach:	They propose a backbone-agnostic, evidence-driven pipeline that treats off-the-shelf MLLMs as interchangeable components to improve stem consistency and figure consistency.
Outcome:	The proposed pipeline improves stem consistency by 1.01-3.18%, figure consistency by 0.50-49.16%, and refusal F1 by 1.06-10.88% across question types.

Copied to clipboard

Jerry Cheung, Yuchen Zhuang, Yinghao Li, Pranav Shetty, Wantian Zhao, Sanjeev Grampurohit, Rampi Ramprasad, Chao Zhang

Information Extraction & Text Mining

Challenge:	SciIE datasets for polymer materials are lacking for this class of materials . POLYIE is curated from 146 full-length polymer scholarly articles .
Approach:	They propose a SciIE dataset for polymer materials that uses entity annotations from 146 full-length articles.
Outcome:	The proposed dataset is curated from 146 full-length polymer scholarly articles . it presents challenges due to diverse lexical formats of entities and ambiguity between entities .

LongTableBench: Benchmarking Long-Context Table Reasoning across Real-World Formats and Domains (2025.findings-emnlp)

Copied to clipboard

Liyao Li, Jiaming Tian, Hao Chen, Wentao Ye, Chao Ye, Haobo Wang, Ningtao Wang, Xing Fu, Gang Chen, Junbo Zhao

Minimal, Local, and Robust: Embedding-Only Edits for Implicit Bias in T2I Models (2025.emnlp-main)

Challenge:	Evaluating 52 LLMs reveals that only the strongest models maintain robust performance under increasing context lengths and format diversity.
Approach:	They propose a benchmark for evaluating long-context reasoning over semi-structured tables across diverse formats, tasks, and domains.
Outcome:	The proposed model outperforms compression-based approaches on tasks requiring semantic integration.

Copied to clipboard

Feng He, Chao Zhang, Zhixue Zhao