Papers by Ping Wang

HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference (2025.findings-acl)

Challenge:	Different Open Information Extraction (OIE) tasks require different types of information.
Approach:	They propose to adapt an OIE Graph to different OIE tasks with simple rules . they implement an end-to-end OIA generator and make it open-accessible .
Outcome:	The proposed system achieves new SOTA performance on three popular OIE tasks.

Copied to clipboard

Ping Gong, Jiawei Yi, Shengnan Wang, Juncheng Zhang, Zewen Jin, Ouxiang Zhou, Ruibo Liu, Guanbin Xu, Youhui Bai, Bowen Ye, Kun Yuan, Tong Yang, Gong Zhang, Renhai Chen, Feng Wu, Cheng Li

Green & Sustainable NLP

Challenge:	Existing top-k attention methods struggle to strike a balance between efficiency and accuracy.
Approach:	They propose a top-k attention approach that integrates low-overhead techniques into the Top-k Attention process to achieve 7.2 speedup compared to vanilla full attention.
Outcome:	The proposed approach achieves 7.2 speedup compared to current top-k attention methods while maintaining model accuracy.

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

Copied to clipboard

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

Dialogue Systems & Conversational Agents

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.

Efficient Tool Use with Chain-of-Abstraction Reasoning (2025.coling-main)

Copied to clipboard

Silin Gao, Jane Dwivedi-Yu, Ping Yu, Xiaoqing Ellen Tan, Ramakanth Pasunuru, Olga Golovneva, Koustuv Sinha, Asli Celikyilmaz, Antoine Bosselut, Tianlu Wang

Hypergraph based Understanding for Document Semantic Entity Recognition (2024.acl-long)

Challenge:	Recent large language models have made progress at interpreting and executing instructions.
Approach:	They propose a method to decouple general reasoning from specialized knowledge . they propose to use abstract reasoning chains and domain tools to reify each chain .
Outcome:	The proposed method outperforms baseline methods on QA and mathematical reasoning domains.

Copied to clipboard

Qiwei Li, Zuchao Li, Ping Wang, Haojun Ai, Hai Zhao

RACER: Retrieval-Augmented Contextual Rapid Speculative Decoding (2026.findings-acl)

Challenge:	Existing document understanding models focus on entity categories while ignoring the extraction of entity boundaries.
Approach:	They propose a hypergraph attention document semantic entity recognition framework which uses hypergraph focus to focus on entity boundaries and entity categories at the same time.
Outcome:	The proposed framework can improve the performance of existing models on FUNSD, CORD, XFUND and SROIE.

Copied to clipboard

Zihong Zhang, Zuchao Li, Lefei Zhang, Ping Wang, Hai Zhao

TRACE: Traversal Retrieval-Augmented Chain of Evidence for Document Understanding (2026.acl-long)

Challenge:	Existing methods for decoding large language models generate one token per step, causing high inference latency.
Approach:	They propose a method that integrates retrieved exact patterns with logit-driven future cues.
Outcome:	Experiments on Spec-Bench, HumanEval, and MGSM-ZH show that RACER outperforms training-free methods and accelerates inference.

Copied to clipboard

Liqi He, Zuchao Li, Hao Huang, Ping Wang

LoRA-Flow: Dynamic LoRA Fusion for Large Language Models in Generative Tasks (2024.acl-long)

Challenge:	Long-context Document Visual Question Answering (DocVQA) methods struggle with visual semantics or handling finite context windows.
Approach:	They propose a new approach to longcontext document visual question answering that transforms retrieval into adaptive evidence chain construction using a Bi-Layered Graph.
Outcome:	The proposed approach achieves an average accuracy improvement of 14.07% on M5BookVQA and exhibits robust generalization with a 13.38% gain across four established benchmarks.

Copied to clipboard

Hanqing Wang, Bowen Ping, Shuo Wang, Xu Han, Yun Chen, Zhiyuan Liu, Maosong Sun

Hephaestus: Improving Fundamental Agent Capabilities of Large Language Models through Continual Pre-Training (2025.naacl-long)

Challenge:	LoRA-Flow uses lightweight modules to customize large language models for downstream tasks . previous work on LoRA combination relied on task-level weights for each involved LoRA .
Approach:	They propose a LoRA-Flow approach that uses dynamic weights to adjust the impact of different LoRAs.
Outcome:	The proposed method outperforms baselines with task-level weights on six generative tasks.

Copied to clipboard

Yuchen Zhuang, Jingfeng Yang, Haoming Jiang, Xin Liu, Kewei Cheng, Sanket Lokegaonkar, Yifan Gao, Qing Ping, Tianyi Liu, Binxuan Huang, Zheng Li, Zhengyang Wang, Pei Chen, Ruijie Wang, Rongzhi Zhang, Nasser Zalmout, Priyanka Nigam, Bing Yin, Chao Zhang

Can Large Language Models Be Good Language Teachers? (2025.emnlp-main)

Challenge:	Existing LLMs often rely on complex prompting or extensive fine-tuning to introduce new capabilities while preserving strong generalizability.
Approach:	They propose a large-scale pre-training corpus to enhance LLM agents' capabilities . they use 103B agent-specific data encompassing 76,537 APIs .
Outcome:	The proposed training corpus outperforms open-source LLMs and commercial LLM agents on three agent benchmarks.

Copied to clipboard

LiQing Xu, Qiwei Li, Tianshuo Peng, Zuchao Li, Hai Zhao, Ping Wang

Putting Captions to the Test: Evaluating Video Caption Quality through Multiple-Choice Question Answering (2026.acl-long)

Challenge:	Large language models (LLMs) have achieved remarkable success across diverse domains, but their potential as effective language teachers remains inadequately assessed.
Approach:	They propose a framework to evaluate Chinese language teachers' pedagogical competence against international standards.
Outcome:	The proposed framework evaluates 13 latest multilingual and Chinese LLMs against international standards for Chinese language teachers.

Copied to clipboard

Zizhen Wang, Bo Feng, Zhengfeng Lai, Shiyu Li, Yang Lu, Meng Cao, Ping Huang, Xiaoming Simon Wang

Unleashing the Reasoning Potential of LLMs by Critique Fine-Tuning on One Problem (2025.emnlp-main)

Challenge:	Existing metrics for video captioning are based on text-based comparisons with ground-truth references.
Approach:	They propose a reference-free benchmark that assesses video captions based on their utility . they will release the benchmark to facilitate reproducible research .
Outcome:	The proposed benchmark improves on human-verified, fine-grained questions . it correlates significantly better with human judgments than existing metrics .

Copied to clipboard

Yubo Wang, Ping Nie, Kai Zou, Lijun Wu, Wenhu Chen

DNA: Denoised Neighborhood Aggregation for Fine-grained Category Discovery (2023.emnlp-main)

Challenge:	Critique Fine-Tuning (CFT) is a promising paradigm for unlocking the reasoning capabilities of large language models.
Approach:	They propose a method that leverages critique data generated from a single math problem to improve reasoning accuracy.
Outcome:	The proposed method surpasses one-shot RLVR while requiring 15 to 20 times less compute.

Copied to clipboard

Wenbin An, Feng Tian, Wenkai Shi, Yan Chen, Qinghua Zheng, QianYing Wang, Ping Chen

MT-Video-Bench: A Holistic Video Understanding Benchmark for Evaluating Multimodal LLMs in Multi-Turn Dialogues (2026.findings-acl)

Challenge:	Existing methods to learn compact cluster representations from coarsely labeled data are noisy and degrade the quality of learning.
Approach:	They propose a framework that encodes semantic structures of data into the embedding space . they retrieve k-nearest neighbors of a query as positive keys to capture similarities .
Outcome:	The proposed framework can retrieve more accurate neighbors and outperform state-of-the-art models by a large margin.

Copied to clipboard

Yaning Pan, Qianqian Xie, Guohui Zhang, Zekun Moore Wang, Yongqian Wen, Yuanxing Zhang, Haoxuan Hu, Zhiyu Pan, Yibing Huang, Zhidong Gan, Yonghong Lin, An Ping, Shihao Li, Yanghai Wang, Tianhao Peng, Jiaheng Liu

Natural Language Interfaces

Challenge:	Existing evaluation benchmarks for Multimodal Large Language Models (MLLMs) focus on single-turn question answering, overlooking the complexity of multi-turn dialogues in real-world scenarios.
Approach:	They propose a video understanding benchmark for MLLMs in multi-turn dialogues that assesses six core competencies that focus on perceptivity and interactivity.
Outcome:	The MT-Video-Bench evaluates 1,000 multi-turn dialogues from diverse domains and reveals significant performance discrepancies and limitations in handling multi-turned video dialogues.

LongDPO: Unlock Better Long-form Generation Abilities for LLMs via Critique-augmented Stepwise Information (2025.findings-acl)

Copied to clipboard

Bowen Ping, Jiali Zeng, Fandong Meng, Shuo Wang, Jie Zhou, Shanghang Zhang

Challenge:	Recent advances in large language models have improved their capacity to handle long text inputs, but current models still exhibit unsatisfactory performance in long-form generation.
Approach:	They propose a method to enhance long-form text generation through step-level supervision by leveraging Monte Carlo Tree Search to collect stepwise preference pairs and employ a global memory pool to maintain factual accuracy.
Outcome:	The proposed method improves performance on long-form generation benchmarks while maintaining lossless performance on several general benchmarks.

Faster In-Context Learning for LLMs via N-Gram Trie Speculative Decoding (2025.emnlp-main)

Copied to clipboard

Jinglin Chen, Qiwei Li, Zuchao Li, Baoyuan Qi, Liu Guoming, Haojun Ai, Hai Zhao, Ping Wang

Accurate KV Cache Quantization with Outlier Tokens Tracing (2025.acl-long)

Challenge:	In-Context Learning (ICL) is a key method in prompt engineering, but its long retrieved contexts and limited token throughput will slow reasoning speeds.
Approach:	They propose a method that leverages the overlap between context and model output to generate drafts from the context.
Outcome:	The proposed method achieves the highest mean speedup on Vicuna-7B, Llama2-7B-Chat, and Llma3-8B-Instruct tasks.

Copied to clipboard

Yi Su, Yuechi Zhou, Quantong Qiu, Juntao Li, Qingrong Xia, Ping Li, Xinyu Duan, Zhefeng Wang, Min Zhang

Vista-LLM: Decoupled Query-Guided Visual Token Pruning for Efficient Long-Video Large Language Models (2026.acl-long)

Challenge:	Large Language Models (LLMs) require substantial computational resources during deployment.
Approach:	They propose a method to identify outlier tokens and exclude them from quantization . they find that the method can deliver a 6.4 times reduction in memory usage and a 2.5 times increase in throughput .
Outcome:	The proposed method delivers a 6.4 times reduction in memory usage and a 2.5 times increase in throughput under 2-bit quantization.

Copied to clipboard

Zhenyu Li, Zuchao Li, Ping Wang, Lefei Zhang, Haojun Ai

The ART of LLM Refinement: Ask, Refine, and Trust (2024.naacl-long)

Challenge:	Long-video understanding is bottlenecked by the high cost of processing massive visual tokens.
Approach:	They propose a decoupled framework for query-guided visual token pruning . their method reduces visual tokens by 90% and accelerates inference by 98% .
Outcome:	The proposed framework reduces visual tokens by 90% and accelerates inference while retaining over 98% of baseline performance on average.

Copied to clipboard

Kumar Shridhar, Koustuv Sinha, Andrew Cohen, Tianlu Wang, Ping Yu, Ramakanth Pasunuru, Mrinmaya Sachan, Jason Weston, Asli Celikyilmaz

A Simple yet Efficient Prompt Compression Method for Text Classification Data Annotation Using LLM (2025.coling-industry)

Challenge:	Large Language Models (LLMs) have demonstrated remarkable generative abilities, but can they judge the quality of their own generations and self-improve?
Approach:	They propose a reasoning with a refinement strategy called ART: Ask, Refine, and Trust that asks necessary questions to decide when an LLM should refine its output and uses it to affirm or deny trust.
Outcome:	The proposed reasoning with a refinement strategy achieves a performance gain of +5 points over baselines on two multistep reasoning tasks.

Copied to clipboard

Yiran Xie, Debin Xiao, Ping Wang, Shuming Liu

Zero-Shot Learners for Natural Language Understanding via a Unified Multiple Choice Perspective (2022.emnlp-main)

Challenge:	Existing methods to improve the accuracy of large language models (LLMs) are often impractical due to high costs and time consumption.
Approach:	They propose a method that uses keyword extraction to reduce prompt tokens in text annotation tasks.
Outcome:	The proposed method reduces prompt tokens while maintaining high accuracy.

Copied to clipboard

Ping Yang, Junjie Wang, Ruyi Gan, Xinyu Zhu, Lin Zhang, Ziwei Wu, Xinyu Gao, Jiaxing Zhang, Tetsuya Sakai

Low-Resource NLP

Challenge:	Existing approaches to zero-shot learning are format-agnostic and can address new learning tasks without additional training.
Approach:	They propose a new paradigm for zero-shot learning that is format agnostic and compatible with any format and applicable to a list of language tasks.
Outcome:	The proposed model shows state-of-the-art performance on several benchmarks and produces satisfactory results on tasks such as text classification and commonsense reasoning.

ALERT: Adapt Language Models to Reasoning Tasks (2023.acl-long)

Copied to clipboard

Ping Yu, Tianlu Wang, Olga Golovneva, Badr AlKhamissi, Siddharth Verma, Zhijing Jin, Gargi Ghosh, Mona Diab, Asli Celikyilmaz

From Misleading Queries to Accurate Answers: A Three-Stage Fine-Tuning Method for LLMs (2025.findings-acl)

Challenge:	Large language models have shown increasing in-context learning capabilities with scaling up the model and data sizes.
Approach:	They propose a benchmark and suite of analyses to evaluate reasoning skills of large language models.
Outcome:	The proposed model compares pre-trained and fine-tuned models on tasks that require reasoning skills to solve.

Copied to clipboard

Guocong Li, Weize Liu, Yihang Wu, Ping Wang, Shuaihan Huang, Hongxia Xu, Jian Wu

ACECODER: Acing Coder RL via Automated Test-Case Synthesis (2025.acl-long)

Challenge:	Existing methods focus on correcting the output but overlook the ability of LLMs to detect and correct misleading content in the input itself.
Approach:	They propose a three-stage fine-tuning method that improves LLMs' ability to detect and correct misleading information in input queries.
Outcome:	The proposed method improves accuracy and factuality of LLM responses while also reducing hallucinations.

Copied to clipboard

Huaye Zeng, Dongfu Jiang, Haozhe Wang, Ping Nie, Xiaotong Chen, Wenhu Chen

Programming Languages in NLP

Challenge:	Recent coder models have been driven by supervised fine-tuning, but the potential of reinforcement learning remains unexplored due to the lack of reliable reward data/model in the code domain.
Approach:	They propose a pipeline that generates extensive test-case pairs from existing code data and constructs preference pairs based on pass rates over sampled programs.
Outcome:	The proposed pipeline generates extensive (question, test-cases) pairs from existing code data and trains them with Bradley-Terry loss.

Adaptive Graph Convolutional Network for Knowledge Graph Entity Alignment (2022.findings-emnlp)

Copied to clipboard

Renbo Zhu, Xukun Luo, Meng Ma, Ping Wang

V-MAGE: A Game Evaluation Framework for Assessing Vision-Centric Capabilities in Multimodal Large Language Models (2026.findings-acl)

Challenge:	Entity alignment (EA) aims to identify equivalent entities from different Knowledge Graphs (KGs) noisy neighbors of entities transfer invalid information, drown out equivalent information, and ultimately reduce the performance of EA.
Approach:	They propose a method to deal with neighbor noises to reduce the performance of EA by capturing the differences and complementarities of multiple KGs.
Outcome:	The proposed framework outperforms the state-of-the-art methods in supervised and unsupervised settings.

Copied to clipboard

Xiangxi Zheng, Linjie Li, Zhengyuan Yang, Ping Yu, Alex Jinpeng Wang, Rui Yan, Yuan Yao, Lijuan Wang

Punctuation-Steered Representation Fine-Tuning (2026.acl-short)

Challenge:	Existing static image-text benchmarks are insufficient for evaluating multimodal large language models’ dynamic perception and interactive reasoning abilities.
Approach:	They propose a game-based evaluation framework to assess multimodal large language models’ visual reasoning in dynamic, continuous-space environments.
Outcome:	The proposed framework systematically assesses MLLMs’ visual reasoning in dynamic, continuous-space environments.

Copied to clipboard

Zheng Gong, Ying Sun, Ping Li, Yi Zheng, Zhefeng Wang

SWE-QA-Pro: A Representative Benchmark and Scalable Training Recipe for Repository-Level Code Understanding (2026.findings-acl)

Challenge:	Existing methods for parameter-efficient fine-tuning (PeFT) are limited due to their prohibitive size and computational demands.
Approach:	They propose a method that fine-tunes punctuation representations to achieve performance improvements.
Outcome:	The proposed method improves performance by altering the representation space alone . but it results in suboptimal performance due to the effects of the method on the output .

Copied to clipboard

Songcheng Cai, Zhiheng Lyu, Yuansheng Ni, Xiangchao Chen, Baichuan Zhou, Shenzhe Zhu, Yi Lu, Haozhe Wang, Chi Ruan, Benjamin Schneider, Weixu Zhang, Xiang Li, Andy Zheng, Yuyu Zhang, Ping Nie, Wenhu Chen

Constructing Your Model’s Value Distinction: Towards LLM Alignment with Anchor Words Tuning (2025.findings-emnlp)

Challenge:	Existing benchmarks for agentic repository-level code understanding overlook long tail topics and rely on memorized knowledge.
Approach:	They propose a repository-level agentic code understanding benchmark that uses long-tail repositories with executable environments to enforce topical balance.
Outcome:	Empirically, a Qwen3-8B model trained with the proposed benchmark outperforms GPT-4o by 2.3 points.

Copied to clipboard

Zhen Yang, Ping Jian, Chengzhi Li, Chenxu Wang, Xinyue Zhang, Wenpeng Lu

Challenge:	a study of large language models (LLMs) shows that they can generate outputs that are honest, positive, harmless, etc.
Approach:	They propose a method that amplifies logits difference between positive and negative tokens . they propose to use the logits gap to generate positive and positive tokens after alignment .
Outcome:	The proposed method achieves effective alignment, but requires fewer computational resources compared to training-time alignment methods.

Plot2Code: A Comprehensive Benchmark for Evaluating Multi-modal Large Language Models in Code Generation from Scientific Plots (2025.findings-naacl)

Copied to clipboard

Chengyue Wu, Zhixuan Liang, Yixiao Ge, Qiushan Guo, Zeyu Lu, Jiahao Wang, Ying Shan, Ping Luo

Prompt-based Logical Semantics Enhancement for Implicit Discourse Relation Recognition (2023.emnlp-main)

Challenge:	Multi-modal Large Language Models have shown remarkable progress in visual contexts, yet their ability to convert visual figures into executable code remains underexplored.
Approach:	They propose to use a set of visual coding metrics to assess MLLMs' visual . pass rate, text-match ratio, and GPT-4V rating judgement to assess the quality of generated code and rendered images.
Outcome:	The proposed benchmark includes 132 high-quality matplotlib plots across six plot types, as well as 150 and 86 plots from Python’s and R’s plotly libraries respectively, totaling 368 plots.

Copied to clipboard

Chenxu Wang, Ping Jian, Mu Huang

Fine-grained Category Discovery under Coarse-grained supervision with Hierarchical Weighted Self-contrastive Learning (2022.emnlp-main)

Challenge:	Existing methods for identifying discourse relations without explicit connectives are limited by the availability of annotated data.
Approach:	They propose a method that injects knowledge relevant to discourse relation into pre-trained language models through prompt-based connective prediction.
Outcome:	The proposed method achieves outstanding performance against the current state-of-the-art models.

Copied to clipboard

Wenbin An, Feng Tian, Ping Chen, Siliang Tang, Qinghua Zheng, QianYing Wang

Adaptive Zooming via Relevance-Informed Positional Resource Allocation for Training-free LLM Context Extension (2026.findings-acl)

Challenge:	Existing methods for novel category discovery focus on the scenario where known and novel categories are of the same granularity.
Approach:	They propose a novel scenario for fine-grained category discovery under coarse-grain supervision that allows for adapting models to categories of different granularity from known ones.
Outcome:	The proposed model can adapt models to categories of different granularity from known ones and reduce labeling cost.

Copied to clipboard

Hongbo Zhao, Huibin Wang, Bin Tang, Xianming Hu, Yihong Huang, Yijun Shen, Nuoyi Chen, Ping Li, Kai Zhang

NOTA: Multimodal Music Notation Understanding for Visual Large Language Model (2025.findings-naacl)

Challenge:	Existing training-free methods for extrapolating beyond training context lengths are semantics-agnostic . Existing methods that focus on relative token distances can indiscriminately blur semantically relevant and irrelevant tokens .
Approach:	They propose an adaptive positional zooming method that uses semantic relevance to extrapolate beyond training context lengths.
Outcome:	Experiments show that RiPRA outperforms existing training-free extrapolation methods . relevant tokens get higher positional resolution, while irrelevant tokens are compressed .

Copied to clipboard

Mingni Tang, Jiajia Li, Lu Yang, Zhiqiang Zhang, Jinhao Tian, Zuchao Li, Lefei Zhang, Ping Wang

LLaMA Pro: Progressive LLaMA with Block Expansion (2024.acl-long)

Challenge:	Existing general-domain visual language models lack ability of music notation understanding . Symbolic music is represented in two distinct forms: auditory music and symbolic music .
Approach:	They propose to train a multimodal music notation model using a large-scale dataset . they use cross-modal alignment to train the model for music notations analysis .
Outcome:	The proposed model improves on music understanding by training with a multimodal music notation model.

Copied to clipboard

Chengyue Wu, Yukang Gan, Yixiao Ge, Zeyu Lu, Jiahao Wang, Ye Feng, Ying Shan, Ping Luo

Faster MoE LLM Inference for Extremely Large Models (2026.findings-acl)

Challenge:	Existing studies have demonstrated that pre-trained LLMs are limited in certain domains, such as programming, mathematics, biomedical, or finance.
Approach:	They propose a new post-pretraining method with an expansion of Transformer blocks to tune the expanded blocks using only new corpus, efficiently and effectively improving the model’s knowledge while mitigating forgetting.
Outcome:	The proposed model outperforms existing models in programming and math and its instruction-following counterpart LLaMA Pro-8.3B in general tasks, programming, and mathematics.

Copied to clipboard

Haoqi Yang, Luohe Shi, Qiwei Li, Zuchao Li, Ping Wang, Hao Huang, Hai Zhao

BoYaEval: Evaluating Multimodal Large Language Models on Understanding Ancient Chinese Musical Scores (2026.acl-long)

Challenge:	Existing inference optimizations for coarse-grained Mixture-of-Experts models implicitly assume a fixed activation budget, which is poorly understood.
Approach:	They propose a training-free policy that adapts token-level activation using router confidence and entropy while remaining within the model’s original budget.
Outcome:	The proposed skipping policy can provide substantial throughput gains, but optimal static schedules vary significantly across models and routing mechanisms.

Copied to clipboard

Jiajia Li, Weizhi Xue, Yao Yao, Qiwei Li, null Chenchong, Zuchao Li, Ping Wang, Hai Zhao

EVIDENCEMINER: Textual Evidence Discovery for Life Sciences (2020.acl-demos)

Challenge:	Multimodal Large Language Models excel in general tasks but struggle with specialized, structured cultural symbols.
Approach:	They evaluate 21 leading MLLMs and compare their performance to a benchmark for Ancient Chinese musical notation.
Outcome:	The benchmark evaluates 21 leading MLLMs on five types of ancient Chinese music notation systems.

Copied to clipboard

Xuan Wang, Yingjun Guan, Weili Liu, Aabhas Chauhan, Enyi Jiang, Qi Li, David Liem, Dibakar Sigdel, John Caufield, Peipei Ping, Jiawei Han

Where CoT Reasoning Commits: Entropy Traces Identify Interpretable Attention Heads (2026.findings-acl)

Challenge:	EVIDENCEMINER is a web-based system that allows users to query a natural language statement and retrieve textual evidence from a background corpora for life sciences.
Approach:	They propose a web-based system that lets users query a natural language statement and automatically retrieves textual evidence from a background corpora for life sciences.
Outcome:	EVIDENCEMINER is a web-based system that lets users query a natural language statement and automatically retrieves textual evidence from a background corpora for life sciences.

Copied to clipboard

Tianhe Zhang, Yonghong Deng, Ping Jian, Zhen Yang, Boyang Wang, Xinyue Zhang

SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers (2025.acl-long)

Challenge:	a growing body of work suggests a disconnect between the generated rationale and the model's actual choice.
Approach:	They propose a mechanism-aware framework that interprets the evolving "choice state" of attention heads during CoT generation . they identify a set of intervention targets and perform Selective Head Fine-Tuning .
Outcome:	The proposed framework interprets the "choice state" of attention heads during CoT generation . it detects two functional behaviors: Steadfast Heads and Wavering Heads .

Copied to clipboard

Zicong Tang, Shi Luohe, Zuchao Li, Baoyuan Qi, Liu Guoming, Lefei Zhang, Ping Wang

Challenge:	Large language models (LLMs) have impressive capabilities across various fields, but their widespread use is facing a severe and realistic challenge, which is their high demand for GPU memory.
Approach:	They propose a KV cache reduction method which balances both shallow and deep layers by using an attention weight based eviction method and a codebook based replacement approach.
Outcome:	The proposed method reduces the KV cache for shallower layers while preserving similar or even better model performance.

The Music Maestro or The Musically Challenged, A Massive Music Evaluation Benchmark for Large Language Models (2024.findings-acl)

Copied to clipboard

Jiajia Li, Lu Yang, Mingni Tang, Chenchong Chenchong, Zuchao Li, Ping Wang, Hai Zhao

UniEX: An Effective and Efficient Framework for Unified Information Extraction via a Span-extractive Perspective (2023.acl-long)

Challenge:	Existing benchmarks to evaluate LLMs' capabilities are inadequate for assessing their musical capabilities.
Approach:	They propose to use a large-scale music benchmark specifically designed to evaluate the music-related capabilities of large language models (LLMs).
Outcome:	The proposed framework evaluates 16 large language models in the domain of music.

Copied to clipboard

Yang Ping, JunYu Lu, Ruyi Gan, Junjie Wang, Yuxiang Zhang, Pingjian Zhang, Jiaxing Zhang

XDailyDialog: A Multilingual Parallel Dialogue Corpus (2023.acl-long)

Challenge:	Existing approaches for information extraction (IE) are limited by the number of subtasks and the isolation of the subtask.
Approach:	They propose a new paradigm for universal information extraction that is compatible with any schema format and applicable to a list of IE tasks.
Outcome:	The proposed framework outperforms generative universal IE models on 14 benchmarks with the supervised setting and the state-of-the-art performance in low-resource scenarios.

Copied to clipboard

Zeming Liu, Ping Nie, Jie Cai, Haifeng Wang, Zheng-Yu Niu, Peng Zhang, Mrinmaya Sachan, Kaiping Peng

Natural Language Interfaces

Challenge:	Existing datasets for open-domain dialogue modeling limited to a single language . absence of multilingual datasets hinders development of robust open- domain dialog systems .
Approach:	They propose a multilingual parallel open-domain dialog dataset to explore multilingual and cross-lingual open- domain dialog.
Outcome:	The proposed model can be used to explore multilingual and cross-lingual open-domain dialogs in other languages.

Lightweight LLM Agent Memory with Small Language Models (2026.acl-long)

Copied to clipboard

Jiaquan Zhang, Chaoning Zhang, Shuxu Chen, Zhenzhen Huang, Pengcheng Zheng, Zhicheng Wang, Ping Guo, Fan Mo, Sung-Ho Bae, Jie Zou, Jiwei Wei, Yang Yang

Few-Shot Text Classification with Edge-Labeling Graph Neural Network-Based Prototypical Network (2020.coling-main)

Challenge:	Existing external memory systems for LLMs have low online overhead but are unstable in accumulating latency over long interactions.
Approach:	They propose a lightweight memory system for better agent memory driven by Small Language Models . lightmem modularizes memory retrieval, writing, and long-term consolidation . they show consistent gains across model scales and high efficiency .
Outcome:	The proposed system improves agent memory but has low latency and low online overhead . it separates online processing from offline consolidation to enable efficient memory invocation . the proposed system achieves an average F1 improvement of 2.5 over A-MEM on LoCoMo .

Copied to clipboard

Chen Lyu, Weijie Liu, Ping Wang

From 128K to 4M: Efficient Training of Ultra-Long Context Large Language Models (2026.findings-acl)

Challenge:	a few-shot text classification method is proposed to solve the few-sshot text problem . supervised learning methods require large corpus of labeled data, making them hindered in practical application.
Approach:	They propose a few-shot text classification method that takes advantage of advanced pre-trained language models to extract the semantic features of each document.
Outcome:	The proposed method achieves state-of-the-art on sentiment analysis and relation datasets.

Copied to clipboard

Chejian Xu, Wei Ping, Peng Xu, Zihan Liu, Boxin Wang, Mohammad Shoeybi, Bo Li, Bryan Catanzaro

Debate-of-Thoughts: Resolving Knowledge Conflicts in LLMs Through Internal Deliberation (2026.acl-long)

Challenge:	Long-context capabilities are essential for document and video understanding, in-contact learning, and inference-time scaling.
Approach:	They propose an efficient training recipe for building ultra-long context LLMs from aligned instruct model, pushing the boundaries of context lengths from 128K to 1M, 2M, and 4M tokens.
Outcome:	The proposed model extends the context window while maintaining short context capabilities while maintaining the performance of the existing model.

Copied to clipboard

Guocong Li, Qirui Hu, Ping Wang, Guofeng Zhang, Jian Wu, Hongxia Xu

Shall We Pretrain Autoregressive Language Models with Retrieval? A Comprehensive Study (2023.emnlp-main)

Challenge:	Existing methods for retrieval augmented generation are based on a simplistic binary choice of relying on external contexts or memory.
Approach:	They propose a framework that transforms conflict resolution into an active deliberation process by incorporating contradictions as opportunities for deeper reasoning.
Outcome:	Experiments show that DoT outperforms state-of-the-art methods while generating transparent debate transcripts that explain its decisions.

Copied to clipboard

Boxin Wang, Wei Ping, Peng Xu, Lawrence McAfee, Zihan Liu, Mohammad Shoeybi, Yi Dong, Oleksii Kuchaiev, Bo Li, Chaowei Xiao, Anima Anandkumar, Bryan Catanzaro

CharTide: Data-Centric Chart-to-Code Generation via Tri-Perspective Tuning and Inquiry-Driven Evolution (2026.acl-long)

Challenge:	a recent study shows that retrieval-augmented LMs can improve text generation quality and accuracy.
Approach:	They propose a model that reproduces RETRO parameters while retrieving a text corpus . they find RETRO outperforms GPT on text generation with less repetition .
Outcome:	The proposed model outperforms standard retrieval-augmented GPT and retrieval augmented GTP on text generation and accuracy tasks.

Copied to clipboard

Xiangxi Zheng, Kuang He, Jiayi Hu, Ping Yu, Rui Yan, Yuan Yao, Peng Hou, Anxiang Zeng, Alex Jinpeng Wang

The Dark Side of Function Calling: Pathways to Jailbreaking Large Language Models (2025.coling-main)

Challenge:	Existing approaches to chart-to-code generation are constrained by data-centric limitations . authors present a new framework that redesigns both training and alignment data .
Approach:	They propose a data-centric framework that redesigns both training and alignment data for chart-to-code generation.
Outcome:	The proposed framework outperforms open-source baselines and is competitive with GPT-5.

Copied to clipboard

Zihui Wu, Haichang Gao, Jianping He, Ping Wang

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

Challenge:	Large language models (LLMs) have remarkable capabilities, but their security implications have been overlooked.
Approach:	They propose a “jailbreak function” attack method that exploits alignment discrepancies, user coercion, and the absence of rigorous safety filters.
Outcome:	The proposed attack exploits alignment discrepancies, user coercion, and the absence of rigorous safety filters on six state-of-the-art LLMs.

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

Selective Prefix Tuning for Pre-trained Language Models (2024.findings-acl)

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

Hongyi Zhang, Zuchao Li, Ping Wang, Hai Zhao

Generalized Category Discovery with Large Language Models in the Loop (2024.findings-acl)

Challenge:	Existing methods for fine-tuning pre-trained models are time-consuming and memory-inefficient.
Approach:	They propose a method that inserts learnable vectors into each Transformer layer . they propose SL to encourage diversity in prefix tokens .
Outcome:	Extensive experiments validate the effectiveness of Prefix Tuning in sentence and token classification tasks.

Copied to clipboard

Wenbin An, Wenkai Shi, Feng Tian, Haonan Lin, QianYing Wang, Yaqiang Wu, Mingxiang Cai, Luyan Wang, Yan Chen, Haiping Zhu, Ping Chen

A Diffusion Weighted Graph Framework for New Intent Discovery (2023.emnlp-main)

Challenge:	Generalized Category Discovery (GCD) is a crucial task that aims to recognize both known and novel categories from a set of unlabeled data.
Approach:	They propose a framework that introduces Large Language Models into the training loop to generate category names without human effort.
Outcome:	The proposed framework outperforms SOTA models on three benchmark datasets and generates accurate category names for the discovered clusters.

Copied to clipboard

Wenkai Shi, Wenbin An, Feng Tian, Qinghua Zheng, QianYing Wang, Ping Chen

LeafNATS: An Open-Source Toolkit and Live Demo System for Neural Abstractive Text Summarization (N19-4)

Challenge:	Existing methods to learn from unlabeled data generate noisy supervisory signals . current methods only rely on semantic similarities to generate supervisory signal .
Approach:	They propose a weighted DWGF framework to capture semantic similarities and structure relationships in data.
Outcome:	The proposed method outperforms state-of-the-art models on evaluation metrics across multiple benchmark datasets.

Copied to clipboard

Tian Shi, Ping Wang, Chandan K. Reddy

Text Generation

Challenge:	Neural abstractive text summarization (NATS) has gained a lot of attention in the past few years from both industry and academia.
Approach:	They propose an open-source toolkit for training and evaluation of different sequence-to-sequence based models for the NATS task and for deploying the pre-trained models to real-world applications.
Outcome:	The proposed model can be used to generate high-quality summaries that are verbally innovative and can easily incorporate external knowledge.

VHASR: A Multimodal Speech Recognition System With Vision Hotwords (2024.emnlp-main)

Copied to clipboard

Jiliang Hu, Zuchao Li, Ping Wang, Haojun Ai, Lefei Zhang, Hai Zhao

Surprise Calibration for Better In-Context Learning (2025.emnlp-main)

Challenge:	Existing models that incorporate audio-related image information do not improve speech recognition performance.
Approach:	They propose a novel approach utilizing audio-related image information and set up a multimodal speech recognition system that uses vision as hotwords to enhance the model’s speech recognition capability.
Outcome:	The proposed model outperforms unimodal ASR model and achieves SOTA among existing image-based multimodal ASL models.

Copied to clipboard

Zhihang Tan, Jingrui Hou, Ping Wang, Qibiao Hu, Peng Zhu

From Bottom to Top: Extending the Potential of Parameter Efficient Fine-Tuning (2024.emnlp-main)

Challenge:	Existing methods for in-context learning apply fixed class priors across all inputs . existing methods rely on retraining and retrain models .
Approach:	They propose a Bayesian-based method to capture the temporal dynamics of class priors . they identify "surprise" as an informative signal for class prior shift .
Outcome:	The proposed method outperforms existing methods on a range of benchmark tasks.

Copied to clipboard

Jihao Gu, Zelin Wang, Yibo Zhang, Ziji Zhang, Ping Gong

Memory or Reasoning? Explore How LLMs Compute Mixed Arithmetic Expressions (2025.findings-acl)

Challenge:	Existing methods to fine-tune large language models primarily focus on the interaction between different layers, ignoring the fact that different layers store different information.
Approach:	They propose a Parameter Efficient Fine-Tuning method which freeze pre-trained parameters and fine-tunes only a few task-specific parameters.
Outcome:	The proposed methods reduce parameter count to nearly half by omitting fine-tuning in the middle layers.

Copied to clipboard

Chengzhi Li, Heyan Huang, Ping Jian, Zhen Yang, Chenxu Wang, Yifan Wang

Enhancing Ancient Chinese Understanding with Derived Noisy Syntax Trees (2023.acl-srw)

Challenge:	Large language models (LLMs) can solve complex multi-step math reasoning problems, but their internal implementation is limited.
Approach:	They propose to use a "Causal Effect Driven F**ine-tuning method" to improve LLMs' reasoning ability.
Outcome:	The proposed method improves the model's reasoning ability by enhancing key components that are used to execute mixed arithmetic calculations.

Copied to clipboard

Ping Wang, Shitou Zhang, Zuchao Li, Jingrui Hou

EfficientQAT: Efficient Quantization-Aware Training for Large Language Models (2025.acl-long)

Challenge:	Syntactic information is not used in modern Chinese understanding tasks due to the lack of syntactical annotation.
Approach:	They propose a confidence-based syntax encoding network to alleviate the side effects of unsupervised syntax derivation and the incompatibility between ancient and modern Chinese.
Outcome:	The proposed component alleviates side effects from unsupervised syntax derivation and incompatibility between ancient and modern Chinese.

Copied to clipboard

Mengzhao Chen, Wenqi Shao, Peng Xu, Jiahao Wang, Peng Gao, Kaipeng Zhang, Ping Luo

A Predicate-Function-Argument Annotation of Natural Language for Open-Domain Information eXpression (2020.emnlp-main)

Challenge:	Quantization-aware training (QAT) is a low-bit training solution that requires substantial training resources.
Approach:	They propose an algorithm that reduces memory consumption by low-bit representations with minimal accuracy loss.
Outcome:	EfficientQAT achieves 2-bit Llama-2-70B model on single GPU in 41 hours . compared to previous methods, it obtains model with less than 3 points accuracy degradation .

Copied to clipboard

Mingming Sun, Wenyue Hua, Zoey Liu, Xin Wang, Kangjie Zheng, Ping Li

Open Information Extraction

Challenge:	Existing OIE (Open Information Extraction) algorithms are redundant and not reusable.
Approach:	They propose a pipeline where an Open-domain Information eXpression task provides a platform for all OIE strategies.
Outcome:	The proposed pipeline provides a platform for all OIE strategies.

Can LLMs See Without Pixels? Benchmarking Spatial Intelligence from Textual Descriptions (2026.findings-acl)

Copied to clipboard

Zhongbin Guo, Zhen Yang, Yushan Li, Xinyue Zhang, Wenyu Gao, Jiacheng Wang, Chengzhi Li, Xiangrui Liu, Ping Jian

Label Drop for Multi-Aspect Relation Modeling in Universal Information Extraction (2025.naacl-long)

Challenge:	Existing advances in Spatial Intelligence rely on vision-Language Models . however, a critical question remains: does spatial understanding originate from visual encoders?
Approach:	They propose to evaluate the SI performance of Large Language Models without pixel-level input.
Outcome:	The proposed benchmark challenges large language models to perform symbolic reasoning rather than visual pattern matching.

Copied to clipboard

Lu Yang, Jiajia Li, En Ci, Lefei Zhang, Zuchao Li, Ping Wang

Dialogue-RAG: Enhancing Retrieval for LLMs via Node-Linking Utterance Rewriting (2025.acl-long)

Challenge:	Extractive UIEs can solve model explosion problems using a relatively small model . single-target instruction UIE enables the extraction of only one type of relation at a time .
Approach:	They propose a model that assigns different relations to different levels for understanding and decision-making.
Outcome:	Experiments show that LDNet outperforms state-of-the-art systems on 9 tasks, 33 datasets . LDnet outperformed state- of-the art systems on single-modal and multi-modal tasks .

Copied to clipboard

Qiwei Li, Teng Xiao, Zuchao Li, Ping Wang, Mengjia Shen, Hai Zhao

Paraphrasing

Challenge:	Large Language Models (LLMs) and Retrieval Augmented Generation (RAG) methods have demonstrated significant potential on tasks across multiple domains.
Approach:	They propose a lightweight IUR model for query rewriting to complete key information in dialogue to enhance retrieval.
Outcome:	The proposed model improves retrieval and generation ability of RAG system in multi-round dialogue scenarios.

Fuzzy Reasoning Chain (FRC): An Innovative Reasoning Framework from Fuzziness to Clarity (2025.findings-emnlp)

Copied to clipboard

Ping Chen, Xiang Liu, Zhaoxiang Liu, Zezhou Chen, Xingpeng Zhang, Huan Hu, Zipeng Wang, Kai Wang, Shuming Shi, Shiguo Lian