Papers by Jiayi Zhang

OCR-Memory: Optical Context Retrieval for Long-Horizon Agent Memory (2026.acl-long)

Challenge:	Using generic and efficient benchmark generators, human annotators are limited by inefficiency . current benchmark generator methods rely on seed signals, leading to long cycles and high costs .
Approach:	They propose a framework to evaluate LLMs as generic benchmark generators and integrate them as BenchMaker.
Outcome:	The proposed framework achieves comparable performance to human-annotated benchmarks on most metrics.

Copied to clipboard

Jinze Li, Yang Zhang, Xin Yang, Jiayi QU, Jinfeng Xu, Shuo Yang, Junhua Ding, Edith Cheuk-Han Ngai

Disentangle to Decay: Linear Attention with Trainable Decay Factor (2025.coling-main)

Challenge:	Existing LLMs are limited by text-context budgets, resulting in token-expensive storage of raw trajectories . Optical Context Retrieval Memory (OCR-Memory) renders historical tra-jectorios into images annotated with unique visual identifiers.
Approach:	They propose a framework that leverages the visual modality as a high-density representation of agent experience.
Outcome:	Optical Context Retrieval Memory (OCRM) renders historical trajectories into images annotated with unique visual identifiers.

Copied to clipboard

Haibo Tong, Chenyang Zhang, Jiayi Lin, Bingxuan Hou, Qingqing Hong, Junli Wang

DANLI: Deliberative Agent for Following Natural Language Instructions (2022.emnlp-main)

Challenge:	Existing linear attention models use a decay factor based positional encoding (PE), but the decay factor is manually designed and non-trainable, limiting further optimization.
Approach:	They propose a PE-based positional encoding that disentangles decay factor into two parts to achieve further optimization and stable training.
Outcome:	The proposed model achieves stable training of decay factor and improves inference efficiency in normal context and extrapolation scenarios.

Copied to clipboard

Yichi Zhang, Jianing Yang, Jiayi Pan, Shane Storks, Nikhil Devraj, Ziqiao Ma, Keunwoo Yu, Yuwei Bao, Joyce Chai

Understanding and Mitigating Political Stance Cross-topic Generalization in Large Language Models (2026.acl-long)

Challenge:	Recent work on embodied AI agents that can perform tasks by following human language instructions is limited by reactive methods, which are insufficient for long-horizon complex tasks.
Approach:	They propose a neuro-symbolic deliberative agent that, while following language instructions, proactively applies reasoning and planning based on its neural and symbolic representations acquired from past experience.
Outcome:	The proposed agent achieves greater than 70% improvement over reactive baselines on the challenging TEACh benchmark.

Copied to clipboard

Jiayi Zhang, Shu Yang, Junchao Wu, Derek F. Wong, Di Wang

RAG-Star: Enhancing Deliberative Reasoning with Retrieval Augmented Verification and Refinement (2025.naacl-long)

Challenge:	Recent studies have focused on the internal representations of large language models and the mechanisms that lead to unintended cross-topic generalization.
Approach:	They propose a method that uses inhibition to localize political neurons and a technique that uses topic-specific blocking to mitigate the cross-topic generalization.
Outcome:	The proposed method reduces cross-topic generalization by 20% while preserving topic-specific performance.

Copied to clipboard

Jinhao Jiang, Jiayi Chen, Junyi Li, Ruiyang Ren, Shijie Wang, Xin Zhao, Yang Song, Tao Zhang

Data Interpreter: An LLM Agent for Data Science (2025.findings-acl)

Challenge:	Existing large language models (LLMs) show exceptional problem-solving capabilities but struggle with complex reasoning tasks.
Approach:	They propose a novel RAG approach that integrates retrieved information to guide tree-based reasoning process based on LLMs.
Outcome:	The proposed approach outperforms existing methods in large language models . iteratively plans intermediate sub-queries and answers based on the LLM itself .

Copied to clipboard

Sirui Hong, Yizhang Lin, Bang Liu, Bangbang Liu, Binhao Wu, Ceyao Zhang, Danyang Li, Jiaqi Chen, Jiayi Zhang, Jinlin Wang, Li Zhang, Lingyao Zhang, Min Yang, Mingchen Zhuge, Taicheng Guo, Tuo Zhou, Wei Tao, Robert Tang, Xiangtao Lu, Xiawu Zheng, Xinbing Liang, Yaying Fei, Yuheng Cheng, Yongxin Ni, Zhibin Gou, Zongze Xu, Yuyu Luo, Chenglin Wu

Understanding How Value Neurons Shape the Generation of Specified Values in LLMs (2025.findings-emnlp)

Challenge:	Large Language Models (LLMs) excel in various domains but face challenges when applied to data science workflows due to their complex, multi-stage nature.
Approach:	They propose a hierarchical graph-based agent that represents complexity and a progressive strategy for step-by-step verification, refinement, and consistent context management.
Outcome:	The proposed agent surpasses state-of-the-art baselines on the MATH dataset and performs better on InfiAgent-DABench.

Copied to clipboard

Yi Su, Jiayi Zhang, Shu Yang, Xinhai Wang, Lijie Hu, Di Wang

Explainability & Interpretability in NLP

Challenge:	Current approaches to interpret value representations are limited by superficial judgments over mechanistic analysis.
Approach:	They propose a mechanistic interpretability framework that uses the Schwartz Values Survey to interpret value . they use a dataset that operationalizes four dimensions of universal value through behavioral contexts .
Outcome:	The proposed method bridges psychological value frameworks with neuron analysis in large language models.

Mixture-of-Minds: Multi-Agent Reinforcement Learning for Table Understanding (2026.acl-long)

Copied to clipboard

Yuhang Zhou, Mingrui Zhang, Ke Li, Mingyi Wang, Qiao Liu, Qifei Wang, Jiayi Liu, Fei Liu, Serena Li, Weiwei LI, Mingze Gao, Abhishek Kumar, Xiangjun Fan, Zhuokai Zhao, Lizhu Zhang

Self-Supervised Prompt Optimization (2025.findings-emnlp)

Challenge:	Large language models (LLMs) have shown promise on understanding and reasoning over tables, but current approaches remain limited.
Approach:	They propose a multi-agent framework that decomposes table reasoning into three specialized roles: planning, coding, and answering.
Outcome:	The proposed framework decomposes table reasoning into three specialized roles: planning, coding, and answering.

Copied to clipboard

Jinyu Xiang, Jiayi Zhang, Zhaoyang Yu, Xinbing Liang, Fengwei Teng, Jinhao Tu, Fashen Ren, Xiangru Tang, Sirui Hong, Chenglin Wu, Yuyu Luo

Low-Resource NLP

Challenge:	Existing prompt optimization methods rely heavily on external references such as ground truth or by humans, limiting their applicability in real-world scenarios where such data is unavailable or costly to obtain.
Approach:	They propose a cost-efficient framework that discovers effective prompts for both closed and open-ended tasks without external reference.
Outcome:	The proposed framework outperforms state-of-the-art prompt optimization methods with significantly lower costs and fewer samples.

InsBank: Evolving Instruction Subset for Ongoing Alignment (2025.findings-emnlp)

Copied to clipboard

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

FLAT-LLM: Fine-grained Low-rank Activation Space Transformation for Large Language Model Compression (2026.findings-eacl)

Challenge:	Recent studies emphasize that quality and diversity of instruction data are more crucial than quantity, highlighting the need to select diverse, high-quality subsets to reduce training costs.
Approach:	They propose to use a continuously updated repository to integrate the latest valuable instruction data with a progressive evolution framework to evolve InsBank over time.
Outcome:	The proposed framework outperforms baselines in InsBank evolution and extracts budget-specific subsets.

Copied to clipboard

Jiayi Tian, Ryan Solgi, Jinming Lu, Yifan Yang, Hai Li, Zheng Zhang

Focus-Constrained Attention Mechanism for CVAE-based Response Generation (2020.findings-emnlp)

Challenge:	Low-rank decomposition methods suffer from accuracy degradation and expensive calibration procedures.
Approach:	They propose a fast and accurate, training-free structural compression method based on fine-grained low-rank transformations in the activation space.
Outcome:	The proposed method outperforms pruning baselines in generalization and downstream performance while delivering inference speedups.

Copied to clipboard

Zhi Cui, Yanran Li, Jiayi Zhang, Jianwei Cui, Chen Wei, Bin Wang

Text Generation

Challenge:	Existing models generate high-frequency but trivial responses such as "I don't know" or "I'm ok" due to the discrepancy in discourse-level information, standard models generate one-to-many relationships.
Approach:	They propose to transform coarse-grained discourse-level information into fine-grounded word-level knowledge by introducing a fine-grain focus signal and a focus-constrained attention mechanism to take full advantage of focus.
Outcome:	The proposed model can generate more diverse and informative responses compared with state-of-the-art models.

StreamMeCo: Long-Term Agent Memory Compression for Efficient Streaming Video Understanding (2026.findings-acl)

Copied to clipboard

Junxi Wang, Te Sun, Jiayi Zhu, Junxian Li, Haowen Xu, Zichen Wen, Xuming Hu, Zhiyu li, Linfeng Zhang

AdaSwitch: Adaptive Switching between Small and Large Agents for Effective Cloud-Local Collaborative Learning (2024.emnlp-main)

Challenge:	StreamMeCo is an efficient Stream Agent Memory Compression framework for video understanding.
Approach:	They propose an efficient Stream Agent Memory Compression framework that evicts redundant memory nodes and introduces a time-decay memory retrieval mechanism to mitigate performance degradation.
Outcome:	The proposed framework achieves 1.87 speedup in memory retrieval while delivering an average accuracy improvement of 1.0% on three challenging benchmark datasets.

Copied to clipboard

Hao Sun, Jiayi Wu, Hengyi Cai, Xiaochi Wei, Yue Feng, Bo Wang, Shuaiqiang Wang, Yan Zhang, Dawei Yin

Beyond One-Size-Fits-All: Tailored Benchmarks for Efficient Evaluation (2025.acl-long)

Challenge:	Recent advances in large language models have been remarkable . users face a choice between using cloud-based LLMs for generation quality or local-based ones for lower computational cost .
Approach:	They propose a new LLM utilization paradigm that facilitates collaborative operation . they evaluate AdaSwitch across 7 benchmarks and compare it to other LLMs .
Outcome:	The proposed model improves performance of local and cloud agents across 7 benchmarks . it achieves competitive results compared to the cloud agent while utilizing less computational overhead.

Copied to clipboard

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

CHROMIC: Chronological Reasoning Across Multi-Panel Comics (2026.eacl-long)

Challenge:	Existing efficient methods estimate performance of models on large benchmarks, but these methods rely on the assumption that target models have high prediction consistency with source models.
Approach:	They propose a method that conducts customized evaluation tailored to each target model.
Outcome:	The proposed method reduces the MAE of estimates by 31.4% on benchmarks across 300 models.

Copied to clipboard

Bingxuan Hou, Jiayi Lin, Chenyang Zhang, Dapeng Yin, Shuyue Zhu, Qingqing Hong, Mengna Gao, Junli Wang

Guardian-as-an-Advisor: Advancing Next-Generation Guardian Models for Trustworthy LLMs (2026.findings-acl)

Challenge:	Large-scale vision–language models have achieved remarkable progress on various reasoning tasks, but most studies focus on natural photographic images and pay limited attention to multi-panel visual narratives such as comics.
Approach:	They propose a benchmark dataset for chronological reasoning in multi-panel comics that covers six types of reasoning questions and spans both Western and Japanese comic styles.
Outcome:	The proposed dataset covers six types of reasoning questions and spans both Western and Japanese comic styles.

Copied to clipboard

Yue Huang, Haomin Zhuang, Jiayi Ye, Han Bao, Yanbo Wang, Hang Hua, Siyuan Wu, Pin-Yu Chen, Xiangliang Zhang

C3KG: A Chinese Commonsense Conversation Knowledge Graph (2022.findings-acl)

Challenge:	prevailing taxonomies neglect robustness and honesty, yielding safer-on-paper but less useful systems.
Approach:	They propose a soft-gating pipeline where a guardian predicts a binary risk label plus a concise explanation and prepends this advice to the original query for re-inference.
Outcome:	The proposed model maintains safety while reducing over-refusal.

Copied to clipboard

Dawei Li, Yanran Li, Jiayi Zhang, Ke Li, Chen Wei, Jianwei Cui, Bin Wang

Natural Language Interfaces

Challenge:	Existing commonsense knowledge bases organize tuples in an isolated manner, causing problems for chatbots .
Approach:	They create a Chinese commonsense conversation knowledge graph which integrates social commonsensm and dialog flow information.
Outcome:	The proposed graph incorporates social commonsense knowledge and dialog flow information.

P4: Plug-and-Play Discrete Prompting for Large Language Models Personalization (2024.findings-acl)

Copied to clipboard

Yuansen Zhang, Xiao Wang, Tianze Chen, Jiayi Fu, Tao Gui, Qi Zhang

Just Ask One More Time! Self-Agreement Improves Reasoning of Language Models in (Almost) All Scenarios (2024.findings-acl)

Challenge:	Large Language Models (LLMs) exhibit impressive capabilities in following instructions, but manually prompting them to exhibit certain personalities may result in sub-optimal performance.
Approach:	They propose a plug-and-play prompting method to manipulate Large Language Models with distinct human-like personality traits by appending discrete personalized suffixes to query or dialog histories and focusing exclusively on influential tokens.
Outcome:	The proposed method outperforms other prompting methods and model editing methods on four models ranging from 1.1B to 13B and achieves 79.9% accuracy in customizing LLMs’ personalities.

Copied to clipboard

Lei Lin, Jiayi Fu, Pengli Liu, Qingyang Li, Yan Gong, Junchen Wan, Fuzheng Zhang, Zhongyuan Wang, Di Zhang, Kun Gai

Incorporating Causal Analysis into Diversified and Logical Response Generation (2022.coling-1)

Challenge:	chain-of-thought (CoT) prompting has been shown to be effective on complex reasoning tasks, but the naive greedy decoding used in CoT prompting causes the repetitiveness and local optimality.
Approach:	They propose a generalizable ensemble-optimization method that uses a set of reasoning paths to prompt a language model one more time to determine the optimal answer.
Outcome:	The proposed method can be generalized to almost all scenarios where the type of input questions and answer format of reasoning paths may be unknown.

Copied to clipboard

Jiayi Liu, Wei Wei, Zhixuan Chu, Xing Gao, Ji Zhang, Tan Yan, Yulin Kang

Text Generation

Challenge:	Existing generation-based models generate generic and safe responses such as "So am I" or "I don't know"
Approach:	They propose to predict the mediators to preserve relevant information and auto-regressively incorporate the mediator into generating process.
Outcome:	The proposed model generates relevant and informative responses and outperforms the state-of-the-art in terms of automatic metrics and human evaluations.

SLIM: Let LLM Learn More and Forget Less with Soft LoRA and Identity Mixture (2025.naacl-long)

Copied to clipboard

Jiayi Han, Liang Du, Hongwei Du, Xiangguo Zhou, Yiwen Wu, Yuanfang Zhang, Weibo Zheng, Donghong Han

Can LLMs Act as Historians? Evaluating Historical Research Capabilities of LLMs via the Chinese Imperial Examination (2026.acl-long)

Challenge:	balancing the training budget, downstream performance, and general capabilities of large language models remains a challenge in many applications.
Approach:	They propose a mixture of expert framework based on Soft LoRA and Identity Mixture . SLIM allows dynamic routing between LoRA adapters and identity layers .
Outcome:	The proposed framework reduces training cost while maintaining general capabilities . it can be open-sourced upon publication.

Copied to clipboard

Lirong Gao, Zeqing Wang, Yuyan Cai, Jiayi Deng, Yanmei Gu, Yiming Zhang, Jia Zhou, Yanfei Zhang, Junbo Zhao

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

Challenge:	Existing benchmarks assess basic knowledge breadth or lexical understanding, failing to capture higher-order skills that are central to historical research.
Approach:	They propose a benchmark anchored in the Chinese Imperial Examination system that assesses historical knowledge and lexical understanding.
Outcome:	The new benchmark aims to assess the ability of LLMs to process historical materials and documents.

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

Correct after Answer: Enhancing Multi-Span Question Answering with Post-Processing Method (2024.findings-emnlp)

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

Jiayi Lin, Chenyang Zhang, Haibo Tong, Dongyu Zhang, Qingqing Hong, Bingxuan Hou, Junli Wang

Information Retrieval

Challenge:	Prior work focuses on designing specific methods or applying heuristic strategies to encourage models to predict more correct predictions.
Approach:	They propose a framework that uses a post-processing strategy to handle incorrect predictions.
Outcome:	The proposed framework significantly improves the Exact Match scores on multiple MSQA datasets.

Dissecting Logical Reasoning in LLMs: A Fine-Grained Evaluation and Supervision Study (2025.findings-emnlp)

Copied to clipboard

Yujun Zhou, Jiayi Ye, Zipeng Ling, Yufei Han, Yue Huang, Haomin Zhuang, Zhenwen Liang, Kehan Guo, Taicheng Guo, Xiangqi Wang, Xiangliang Zhang

Analyzing the Role of Semantic Representations in the Era of Large Language Models (2024.naacl-long)

Challenge:	Existing benchmarks that rely on final-answer accuracy fail to capture the quality of the reasoning process.
Approach:	They propose a fine-grained evaluation framework that assesses logical reasoning across three dimensions: overall accuracy, stepwise soundness, and representation-level probing.
Outcome:	The proposed framework assesses logical reasoning across three dimensions: overall accuracy, stepwise soundness, and representation-level probing.

Copied to clipboard

Zhijing Jin, Yuen Chen, Fernando Gonzalez Adauto, Jiarui Liu, Jiayi Zhang, Julian Michael, Bernhard Schölkopf, Mona Diab

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

Challenge:	Existing studies show the benefits of semantic representations in NLP tasks . Existing work using AMR is concerned with trainable models .
Approach:	They propose an AMR-driven chain-of-thought prompting method that uses AMR . they propose to use it to predict which input examples AMR may help or hurt on .
Outcome:	The proposed method hurts performance more than it helps on five different tasks.

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.

Lost in the Context: Insufficient and Distracted Attention to Contexts in Preference Modeling (2025.acl-long)

Copied to clipboard

Shihan Dou, Jiayi Chen, Chenhao Huang, Feng Chen, Wei Chengzhi, Huiyuan Zheng, Shichun Liu, Yan Liu, Chenxiao Liu, Chao Xin, Lin Yan, Zongzhang Zhang, Tao Gui, Qi Zhang, Xuanjing Huang

Challenge:	Existing reward models concatenate contexts and responses, but they often ignore crucial segments of the context that are important for evaluating the response quality.
Approach:	They propose a reward model that evaluates the response quality based on a given context and assigns a rewards reward.
Outcome:	The proposed framework significantly improves preference modeling by increasing attention to relevant information within the context and achieves better generalizability.

Prior Relational Schema Assists Effective Contrastive Learning for Inductive Knowledge Graph Completion (2024.lrec-main)

Copied to clipboard

Ruilin Luo, Jiayi Li, Jianghangfan Zhang, Jing Xiao, Yujiu Yang

Beyond Glass-Box Features: Uncertainty Quantification Enhanced Quality Estimation for Neural Machine Translation (2021.findings-emnlp)

Challenge:	Existing knowledge graphs lack robustness and incompleteness to provide link prediction.
Approach:	They propose to capture prior schema-level interactions related to relations by leveraging entity type information and introduce schema-guided negatives to bolster the efficiency of normal contrastive representation learning.
Outcome:	The proposed method achieves state-of-the-art performance on multiple established metrics across multiple datasets for link prediction.

Copied to clipboard

Ke Wang, Yangbin Shi, Jiayi Wang, Yuqi Zhang, Yu Zhao, Xiaolin Zheng

Multilinguality

Challenge:	Quality Estimation (QE) is an essential role in applications of Machine Translation (MT).
Approach:	They propose to fuse uncertainty quantification into a pre-trained cross-lingual language model to predict the translation quality.
Outcome:	The proposed method achieves state-of-the-art on the datasets of WMT 2020 QE shared task.

From Sub-Ability Diagnosis to Human-Aligned Generation: Bridging the Gap for Text Length Control via MarkerGen (2025.acl-long)

Copied to clipboard

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

Challenge:	Existing methods to control text length are lacking in LCTG, posing a major limitation for practical applications.
Approach:	They propose a plug-and-play approach that decomposes LCTG sub-abilities with human patterns as reference and performs detailed error analysis.
Outcome:	The proposed method significantly improves LCTG across various settings, exhibiting outstanding effectiveness and generalizability.

Unlocking Exploration in RLVR: Uncertainty-aware Advantage Shaping for Deeper Reasoning (2026.findings-acl)

Copied to clipboard

Can Xie, Ruotong Pan, Xiangyu Wu, Zhang Yunfei, Jiayi Fu, Tingting Gao, Guorui Zhou

Mis-prompt: Benchmarking Large Language Models for Proactive Error Handling (2025.acl-long)

Challenge:	Reinforcement Learning with Verifiable Rewards (RLVR) has shown significant promise for enhancing the reasoning capabilities of large language models (LLMs).
Approach:	They propose a model-free method that refines credit assignment by leveraging the model's internal uncertainty signals.
Outcome:	Extensive experiments on five mathematical reasoning benchmarks show that the proposed method outperforms strong RLVR baselines on multiple model scales, including 1.5B and 7B.

Copied to clipboard

Jiayi Zeng, Yizhe Feng, Mengliang He, Wenhui Lei, Wei Zhang, Zeming Liu, Xiaoming Shi, Aimin Zhou

GumbelSoft: Diversified Language Model Watermarking via the GumbelMax-trick (2024.acl-long)

Challenge:	Current error-handling works are performed in a passive manner, with explicit error- handling instructions.
Approach:	They propose a new benchmark to analyze LLMs' performance on a mis-prompt benchmark and a dataset to promote further research.
Outcome:	The proposed benchmark shows that current LLMs show poor performance on proactive error handling, and that SFT improves on error handling instances.

Copied to clipboard

Jiayi Fu, Xuandong Zhao, Ruihan Yang, Yuansen Zhang, Jiangjie Chen, Yanghua Xiao

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

Challenge:	Large language models generate human-like content, but they also pose a problem with generation diversity, negatively impacting generation diversity and user experience.
Approach:	They propose a Logits-Addition watermark and three variants that aim to enhance diversity to overcome generation diversity challenges.
Outcome:	The Logits-Addition watermark outperforms the Logits+Trick-based watermark in diversity tests and outperformed other decoding-based methods by 0.1 to 0.3.

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

Distinguishing Non-natural from Natural Adversarial Samples for More Robust Pre-trained Language Model (2022.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

Jiayi Wang, Rongzhou Bao, Zhuosheng Zhang, Hai Zhao

Robustness in NLP

Challenge:	Recent studies on adversarial attacks achieve high success rates against PrLMs, claiming that they are not robust.
Approach:	They propose to use anomaly detector to evaluate PrLMs with more natural adversarial samples to evaluate their robustness.
Outcome:	The proposed method can be used to defend all types of attacks and achieve higher accuracy on adversarial samples and compliant samples than other defense frameworks.

Flow2Code: Evaluating Large Language Models for Flowchart-based Code Generation Capability (2025.findings-acl)

Copied to clipboard

Mengliang He, Jiayi Zeng, Yankai Jiang, Wei Zhang, Zeming Liu, Xiaoming Shi, Aimin Zhou

Programming Languages in NLP

Challenge:	Existing code generation benchmarks neglect flowchart-based code generation . existing benchmarks lack flowcharting-based evaluation, limiting the potential of large language models and minimizing human error.
Approach:	They propose to use flowcharts to evaluate existing LLMs' code generation capabilities.
Outcome:	The proposed benchmarks show that the supervised fine-tuning technique contributes greatly to the models’ performance.

Bold Claims or Self-Doubt? Factuality Hallucination Type Detection via Belief State (2025.findings-emnlp)

Copied to clipboard

Dongyu Zhang, Qingqing Hong, Bingxuan Hou, Jiayi Lin, Chenyang Zhang, Jialin Li, Junli Wang

Easy Guided Decoding in Providing Suggestions for Interactive Machine Translation (2023.acl-long)

Challenge:	Existing studies focus on detecting the presence of hallucinations but lack a systematic classification approach, which hinders deeper exploration of their characteristics.
Approach:	They propose a method to categorize hallucinations into two types: Overconfident and Unaware .
Outcome:	The proposed method categorizes factuality hallucination into two types: Overconfident and Unaware Hallucinations.

Copied to clipboard

Ke Wang, Xin Ge, Jiayi Wang, Yuqi Zhang, Yu Zhao

Multilinguality

Challenge:	In order to improve translation efficiency, human translators perform post-editing on machine translations to correct errors.
Approach:	They propose to use the parameterized objective function of neural machine translation to deal with the TS problem without additional training.
Outcome:	The proposed method improves translation quality by 10.6 BLEU and reduces time overhead by 63.4% on benchmark datasets.

Bridging the Creativity Understanding Gap: Small-Scale Human Alignment Enables Expert-Level Humor Ranking in LLMs (2025.findings-emnlp)

Copied to clipboard

Kuan Lok Zhou, Jiayi Chen, Siddharth Suresh, Reuben Narad, Timothy T. Rogers, Lalit K Jain, Robert D Nowak, Bob Mankoff, Jifan Zhang

Commonsense Reasoning

Challenge:	Large Language Models (LLMs) have shown significant limitations in understanding creative content, as demonstrated by Hessel et al. (2023)’s influential work on the New Yorker Cartoon Caption Contest.
Approach:	They propose to decompose humor understanding into three components and improve each by enhancing visual understanding through improved annotation and utilizing LLM-generated humor reasoning and explanations.
Outcome:	The proposed approach achieves 82.4% accuracy in caption ranking, significantly better than the previous 67% benchmark and matches the performance of world-renowned human experts in this domain.

On Task-personalized Multimodal Few-shot Learning for Visually-rich Document Entity Retrieval (2023.findings-emnlp)

Copied to clipboard

Jiayi Chen, Hanjun Dai, Bo Dai, Aidong Zhang, Wei Wei

Information Retrieval

Challenge:	Visually-rich document entity retrieval (VDER) is an important topic in industrial NLP applications.
Approach:	They propose a task-aware meta-learning framework to tackle the problem of visually-rich document entity retrieval (VDER) they adopt a hierarchical decoder and employ contrastive learning to achieve this goal.
Outcome:	The proposed framework significantly improves the robustness of popular meta-learning baselines.

cAST: Enhancing Code Retrieval-Augmented Generation with Structural Chunking via Abstract Syntax Tree (2025.findings-emnlp)

Copied to clipboard

Yilin Zhang, Xinran Zhao, Zora Zhiruo Wang, Chenyang Yang, Jiayi Wei, Tongshuang Wu

Syntactic Text Processing

Challenge:	Existing line-based chunking heuristics often break semantic structures, splitting functions or merging unrelated code.
Approach:	They propose a structure-aware method that breaks large AST nodes into smaller chunks . this method generates self-contained, semantically coherent units across programming languages .
Outcome:	The proposed method boosts Recall@5 by 4.3 points on RepoEval retrieval and Pass@1 by 2.67 points on SWE-bench generation.

ReasonerRank: Redefining Language Model Evaluation with Ground-Truth-Free Ranking Frameworks (2025.findings-acl)

Copied to clipboard

Jiamu Zhang, Jiayi Yuan, Andrew Wen, Hoang Anh Duy Le, Yu-Neng Chuang, Soo-Hyun Choi, Rui Chen, Xia Hu