Papers by Hao Peng

Learning Joint Semantic Parsers from Disjoint Data (N18-1)

Challenge:	Existing approaches to attention with bounded-memory control (ABC) have a quadratic complexity in sequence lengths, making it prohibitive for long sequences.
Approach:	They propose a new abstraction that bounds memory size to improve efficiency . they propose bounded-memory control, which connects several efficient attention variants .
Outcome:	The proposed approach outperforms existing approaches on language modeling, machine translation, and masked language model finetuning.

Copied to clipboard

Hao Peng, Sam Thomson, Swabha Swayamdipta, Noah A. Smith

Challenge:	Various formal meaning representations have been developed corresponding to different semantic theories.
Approach:	They propose a method to learn a semantic parser from multiple datasets by treating annotations for unobserved formalisms as latent structured variables.
Outcome:	The proposed approach improves on existing methods using unobserved formalisms and underlying corpora.

XLTime: A Cross-Lingual Knowledge Transfer Framework for Temporal Expression Extraction (2022.findings-naacl)

Copied to clipboard

Yuwei Cao, William Groves, Tanay Kumar Saha, Joel Tetreault, Alejandro Jaimes, Hao Peng, Philip Yu

Multilinguality

Challenge:	Temporal Expression Extraction (TEE) is essential for understanding time in natural language.
Approach:	They propose a framework for multilingual Temporal Expression Extraction that leverages pre-trained language models to prompt cross-language knowledge transfer from English to non-English languages.
Outcome:	The proposed framework outperforms the existing SOTA methods on French, Spanish, Portuguese, and Basque by large margins.

How Much Does Attention Actually Attend? Questioning the Importance of Attention in Pretrained Transformers (2022.findings-emnlp)

Copied to clipboard

Michael Hassid, Hao Peng, Daniel Rotem, Jungo Kasai, Ivan Montero, Noah A. Smith, Roy Schwartz

Contextualized Perturbation for Textual Adversarial Attack (2021.naacl-main)

Challenge:	Pretrained language models use the attention mechanism to contextualize input inputs . but, we find that it is not as important as thought for pretrained models .
Approach:	They propose a probing method that replaces input-dependent attention matrices with constant ones.
Outcome:	The proposed method improves performance of pretrained language models without input-dependent attention.

Copied to clipboard

Dianqi Li, Yizhe Zhang, Hao Peng, Liqun Chen, Chris Brockett, Ming-Ting Sun, Bill Dolan

Robustness in NLP

Challenge:	Existing techniques for generating adversarial examples are driven by local heuristic rules that are agnostic to the context, resulting in unnatural and ungrammatical outputs.
Approach:	They propose a ContextuaLized AdversaRial Example generation model that generates fluent and grammatical outputs through a mask-then-infill procedure.
Outcome:	The proposed model outperforms baseline models in terms of attack success rate, textual similarity, fluency and grammaticality.

Twist Decoding: Diverse Generators Guide Each Other (2022.emnlp-main)

Copied to clipboard

Jungo Kasai, Keisuke Sakaguchi, Ronan Le Bras, Hao Peng, Ximing Lu, Dragomir Radev, Yejin Choi, Noah A. Smith

Text Generation

Challenge:	Using a variety of language generation models, ensembling models is challenging during inference.
Approach:	They propose a method that decodes text models that do not assume a shared vocabulary, tokenization or generation order.
Outcome:	The proposed method outperforms models decoded in isolation over various scenarios.

ACENet: Attention Guided Commonsense Reasoning on Hybrid Knowledge Graph (2022.emnlp-main)

Copied to clipboard

Chuzhan Hao, Minghui Xie, Peng Zhang

OmniEvent: A Comprehensive, Fair, and Easy-to-Use Toolkit for Event Understanding (2023.emnlp-demo)

Challenge:	Existing approaches estimate plausibility of candidate choices separately based on their respective KGs, without considering the interference among different choices.
Approach:	They propose an Attention guided Commonsense rEasoning Network to integrate hybrid knowledge into the neural network.
Outcome:	The proposed model outperforms existing methods on CommonsenseQA and OpenbookQA datasets and shows significant performance gains.

Copied to clipboard

Hao Peng, Xiaozhi Wang, Feng Yao, Zimu Wang, Chuzhao Zhu, Kaisheng Zeng, Lei Hou, Juanzi Li

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

Challenge:	Event understanding is fundamental for humans to understand the world.
Approach:	They propose an event understanding toolkit called OmniEvent that is comprehensive and fair . it supports mainstream modeling paradigms and the processing of 15 widely-used datasets .
Outcome:	The toolkit supports mainstream modeling paradigms and the processing of 15 widely-used English and Chinese datasets.

Copied to clipboard

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

MAVEN-ARG: Completing the Puzzle of All-in-One Event Understanding Dataset with Event Argument Annotation (2024.acl-long)

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

Copied to clipboard

Xiaozhi Wang, Hao Peng, Yong Guan, Kaisheng Zeng, Jianhui Chen, Lei Hou, Xu Han, Yankai Lin, Zhiyuan Liu, Ruobing Xie, Jie Zhou, Juanzi Li

A Mixture of h - 1 Heads is Better than h Heads (2020.acl-main)

Challenge:	Existing datasets for event understanding have limited coverage due to complexity of tasks.
Approach:	They propose a dataset that augments MAVEN datasets with event argument annotations . they propose 98,591 events and 290,613 arguments obtained with laborious human annotation .
Outcome:	The proposed dataset is the first all-in-one dataset supporting event detection, event argument extraction, and event relation extraction.

Copied to clipboard

Hao Peng, Roy Schwartz, Dianqi Li, Noah A. Smith

Machine Translation

Challenge:	Evidence has shown that multi-head attentive neural architectures are overparameterized.
Approach:	They propose a multi-head attentive neural architecture that “reallocates” attention heads to different inputs.
Outcome:	The proposed model outperforms baselines on machine translation and language modeling tasks.

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

Copied to clipboard

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

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

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

Copied to clipboard

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

Sentiment Analysis

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

More Data, More Relations, More Context and More Openness: A Review and Outlook for Relation Extraction (2020.aacl-main)

Copied to clipboard

Xu Han, Tianyu Gao, Yankai Lin, Hao Peng, Yaoliang Yang, Chaojun Xiao, Zhiyuan Liu, Peng Li, Jie Zhou, Maosong Sun

Data Mixing Agent: Learning to Re-weight Domains for Continual Pre-training (2026.acl-long)

Challenge:	Existing methods for extracting relational facts from text have been successful . but with explosion of Web text, human knowledge is increasing drastically .
Approach:	They propose to improve relation extraction methods to extract relational facts from text . they analyze existing methods and show promising directions towards more powerful RE .
Outcome:	The proposed methods can extract relational facts from text, but they are still lacking in the current field.

Copied to clipboard

Kailai Yang, Xiao Liu, Lei Ji, Hao Li, Xiao Liang, Zhiwei Liu, Yeyun Gong, Peng Cheng, Mao Yang

Infusing Finetuning with Semantic Dependencies (2021.tacl-1)

Challenge:	Existing methods for reweighting data mixtures rely on manual designation with certain heuristics based on intuition or empirical results.
Approach:	They propose a model-based framework that learns to re-weight domains by reinforcement learning on large quantities of data mixing trajectories with corresponding feedback from an evaluation environment.
Outcome:	The proposed framework outperforms baselines in achieving balanced performance across source and target fields and domain spaces without retraining.

Copied to clipboard

Zhaofeng Wu, Hao Peng, Noah A. Smith

Towards a Mechanistic Understanding of Large Reasoning Models: A Survey of Training, Inference, and Failures (2026.acl-long)

Challenge:	Several diagnostics help to localize the benefits of our approach.
Approach:	They apply convolutional graph encoders to integrate semantic parses into task-specific finetuning.
Outcome:	The proposed approach yields benefits to natural language understanding (NLU) tasks in the GLUE benchmark.

Copied to clipboard

Yi Hu, Jiaqi Gu, Ruxin Wang, Zijun Yao, Hao Peng, Xiaobao Wu, Jianhui Chen, Muhan Zhang, Liangming Pan

FACTCHECKMATE: Preemptively Detecting and Mitigating Hallucinations in LMs (2025.findings-emnlp)

Challenge:	Recent research has shown that reinforcement learning can elicit intriguing emergent reasoning behaviors.
Approach:	They propose a comprehensive survey of the mechanistic understanding of large reasoning models . they organize findings into three core dimensions: 1) training dynamics, 2) reasoning mechanisms, and 3) unintended behaviors.
Outcome:	This paper synthesizes the mechanistic understanding of large reasoning models into three dimensions . authors outline a roadmap for future studies including improved interpretability and methodologies .

Copied to clipboard

Deema Alnuhait, Neeraja Kirtane, Muhammad Khalifa, Hao Peng

WildReward: Learning Reward Models from In-the-Wild Human Interactions (2026.acl-long)

Challenge:	Language models (LMs) hallucinate.
Approach:	They introduce a classifier that predicts whether LMs hallucinate based on model’s hidden states before decoding begins.
Outcome:	The proposed model preemptively detects hallucinations by learning a classifier that predicts whether the LM will hallucinate . if a hallucinomy is detected, FactCheckmate intervenes by adjusting the model’s hidden states to produce more factual outputs.

Copied to clipboard

Hao Peng, Yunjia Qi, Xiaozhi Wang, Zijun Yao, Lei Hou, Juanzi Li

Challenge:	Prior work focused on collecting preference pairs, requiring substantial annotation efforts.
Approach:	They propose a pipeline to extract reliable human feedback from in-the-wild interactions . they propose to use WildChat as an interaction source to train the model .
Outcome:	The proposed model achieves comparable or even superior performance compared to conventional models with improved calibration and cross-sample consistency.

Emotion Transfer with Enhanced Prototype for Unseen Emotion Recognition in Conversation (2025.emnlp-main)

Copied to clipboard

Kun Peng, Cong Cao, Hao Peng, Guanlin Wu, Zhifeng Hao, Lei Jiang, Yanbing Liu, Philip S. Yu

Sentiment Analysis

Challenge:	Existing research on emotion recognition in conversation does not reach a consensus on classification theories . despite this, there is no clear consensus on how to recognize previously unseen emotions in real-world applications.
Approach:	They propose a prototype-based emotion transfer framework that can be used in real-world applications.
Outcome:	The proposed framework shows promise but still faces key challenges in the field of emotion recognition in conversation.

Text Generation with Exemplar-based Adaptive Decoding (N19-1)

Copied to clipboard

Hao Peng, Ankur Parikh, Manaal Faruqui, Bhuwan Dhingra, Dipanjan Das

Text Generation

Challenge:	Empirical results show that the proposed model achieves strong performance and outperforms comparable baselines.
Approach:	They propose a conditioned text generation model that uses a template-based approach to generate content from input text.
Outcome:	The proposed model outperforms baselines on abstractive text summarization and data-to-text generation.

CTRLEval: An Unsupervised Reference-Free Metric for Evaluating Controlled Text Generation (2022.acl-long)

Copied to clipboard

Pei Ke, Hao Zhou, Yankai Lin, Peng Li, Jie Zhou, Xiaoyan Zhu, Minlie Huang

Low-Resource NLP

Challenge:	Existing reference-free metrics have obvious limitations for evaluating controlled text generation models.
Approach:	They propose an unsupervised reference-free metric which evaluates controlled text generation from different aspects by formulating each aspect into multiple text infilling tasks.
Outcome:	The proposed metric has higher correlations with human judgments while obtaining better generalization of evaluating generated texts from different models and with different qualities.

LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks (2025.acl-long)

Copied to clipboard

Yushi Bai, Shangqing Tu, Jiajie Zhang, Hao Peng, Xiaozhi Wang, Xin Lv, Shulin Cao, Jiazheng Xu, Lei Hou, Yuxiao Dong, Jie Tang, Juanzi Li

Backpropagating through Structured Argmax using a SPIGOT (P18-1)

Challenge:	Existing benchmarks on longcontext large language models fail to reflect their deep understanding capabilities across diverse tasks.
Approach:	They propose a benchmark to assess the ability of long-context large language models to handle long-text problems.
Outcome:	The proposed model achieves 50.1% accuracy when directly answering the questions . human experts achieve only 53.7% accuracy under a 15-minute time constraint .

Copied to clipboard

Hao Peng, Sam Thomson, Noah A. Smith

Improving Temporal Relation Extraction with a Globally Acquired Statistical Resource (N18-1)

Challenge:	Structured projection of intermediate gradients (SPIGOT) is a new method for backpropagating through neural networks . structure-based learning methods for natural language processing are increasingly dominated by end-to-end differentiable functions .
Approach:	They propose a structured projection of intermediate gradients method for backpropagating through neural networks that includes hard-decision structured predictions in intermediate layers.
Outcome:	The proposed method improves on two structured NLP pipelines: syntactic-then-semantic dependency parsing and semantic parser followed by sentiment classification.

Copied to clipboard

Qiang Ning, Hao Wu, Haoruo Peng, Dan Roth

Tackling Distractor Documents in Multi-Hop QA with Reinforcement and Curriculum Learning (2026.findings-eacl)

Challenge:	Existing temporal extraction systems that extract temporal relations can be improved by using a resource that provides prior knowledge of the temporal order that events usually follow.
Approach:	They propose to use a probabilistic knowledge base acquired in the news domain to extract temporal relations between events from the New York Times articles over a 20-year span.
Outcome:	The proposed system and resource are both publicly available.

Copied to clipboard

Jerry Huang, Siddarth Madala, Risham Sidhu, Cheng Niu, Hao Peng, Julia Hockenmaier, Tong Zhang

Information Retrieval

Challenge:	Existing work on retrieval-augmented generation systems has shown that retrievers exhibit imperfect recall and precision, limiting downstream performance.
Approach:	They propose a retrieval-augmented generation model that generates answers from larger sets of retrieved contexts.
Outcome:	The proposed model generates answers and cites relevant information from larger sets of retrieved contexts.

LLM-Enhanced Query Generation and Retrieval Preservation for Task-Oriented Dialogue (2025.findings-acl)

Copied to clipboard

Jiale Chen, Xuelian Dong, Wenxiu Xie, Ru Peng, Kun Zeng, Tianyong Hao

Dialogue Systems & Conversational Agents

Challenge:	Existing knowledge retrieval methods for task-oriented dialogues are limited by data scarcity and lack of data to annotate.
Approach:	They propose an LLM-enhanced model of query-guided knowledge retrieval for task-oriented dialogue . they propose to select the most relevant knowledge from retrieved top-K records and incorporate them as prompts to guide a generator in response generation.
Outcome:	The proposed model outperforms state-of-the-art in three benchmarks on three standard benchmarks.

A Joint Learning Framework for Restaurant Survival Prediction and Explanation (2022.emnlp-main)

Copied to clipboard

Xin Li, Xiaojie Zhang, Peng JiaHao, Rui Mao, Mingyang Zhou, Xing Xie, Hao Liao

Explainability & Interpretability in NLP

Challenge:	Recent advances in deep learning have various models that research reviews and interactions for different kinds of tasks, such as predicting restaurant survival.
Approach:	They propose a joint learning framework for explainable restaurant survival prediction based on multi-modal data of user-restaurant interactions and users’ textual reviews.
Outcome:	The proposed framework improves on two datasets showing that it can model restaurant interactions and users’ textual reviews.

From Observation to Understanding: Front-Door Adjustments with Uncertainty Calibration for Enhancing Egocentric Reasoning in LVLMs (2025.findings-acl)

Copied to clipboard

Shenshen Li, Wenxin Meng, Lei Wang, Hao Yang, Chong Peng, Peng Yan, Fumin Shen, Jingkuan Song, Heng Tao Shen, Xing Xu

Low-Resource NLP

Challenge:	Existing methods that adapt LVLMs to egocentric tasks overlook critical agent-environment interactions, limiting their ability to perform egoic reasoning.
Approach:	They propose a zero-shot paradigm to enhance egocentric reasoning by simulating human causal reasoning by formalizing ego-centric reasoning using a structural causal model.
Outcome:	The proposed method improves egocentric reasoning abilities on six tasks.

Measuring and Improving Attentiveness to Partial Inputs with Counterfactuals (2024.findings-emnlp)

Copied to clipboard

Yanai Elazar, Bhargavi Paranjape, Hao Peng, Sarah Wiegreffe, Khyathi Chandu, Vivek Srikumar, Sameer Singh, Noah Smith

Challenge:	Existing studies have found that datasets with paired inputs are prone to spurious correlations, resulting in models trained only on those outperform chance.
Approach:	They propose a counterfactual attentiveness test to measure reliance on spurious correlations by replacing part of the input with its counterpart from a different example.
Outcome:	The proposed method improves models' attentiveness on ten datasets spanning four tasks: natural language inference, reading comprehension, paraphrase detection, and visual & language reasoning.

VerIF: Verification Engineering for Reinforcement Learning in Instruction Following (2025.emnlp-main)

Copied to clipboard

Hao Peng, Yunjia Qi, Xiaozhi Wang, Bin Xu, Lei Hou, Juanzi Li

Challenge:	Best practices for RL in instruction following remain underexplored.
Approach:	They propose a verification method that combines rule-based code verification with LLM-based verification from a large reasoning model.
Outcome:	The proposed method achieves state-of-the-art performance among models of comparable size and generalizes well to unseen constraints.

ActionIE: Action Extraction from Scientific Literature with Programming Languages (2024.acl-long)

Copied to clipboard

Xianrui Zhong, Yufeng Du, Siru Ouyang, Ming Zhong, Tingfeng Luo, Qirong Ho, Hao Peng, Heng Ji, Jiawei Han

Multimodality

Challenge:	a method that extracts experimental procedures from human language into actionable sequences in robotics language is challenging given the complexity of the instructions and context-dependent nature of the instruction.
Approach:	They propose a method that converts actions written in natural language into Python code that can be easily translated into robotics language.
Outcome:	The proposed method can extract experimental procedures from human language into actionable sequences in robotics language.

SimPBL: A Multi-Agent Framework for Project-Based Learning (2026.acl-long)

Copied to clipboard

Daniel Zhang-Li, Joy Jia Yin Lim, Binglin Liu, Shangqing Tu, Zijun Yao, Hao Peng, Jifan Yu, Haoxuan Li, Zhanxin Hao, Ye He, Zekun Li, Jiangyi Wang, Lei Hou, Bin Xu, Xin Cong, Zhiyuan Liu, Huiqin Liu, Yu Zhang, Juanzi Li

Challenge:	Existing LLMs provide partial assistance without modeling these roles, and overly comprehensive help can reduce learner autonomy.
Approach:	They propose a multi-agent framework with an orchestrator agent that provides adaptive scaffolding from interaction logs and collaborator agents that support project work through boundary-aware collaboration.
Outcome:	The proposed framework improves learner examination scores by 14% . it is based on a multi-agent framework with an orchestrator agent .

On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmark (2022.findings-acl)

Copied to clipboard

Hao Sun, Guangxuan Xu, Jiawen Deng, Jiale Cheng, Chujie Zheng, Hao Zhou, Nanyun Peng, Xiaoyan Zhu, Minlie Huang

Dialogue Systems & Conversational Agents

Challenge:	Dialogue safety problems severely limit the real-world deployment of generative conversational models.
Approach:	They propose a taxonomy for dialogue safety specifically designed to capture unsafe behaviors in human-bot dialogue settings.
Outcome:	The proposed taxonomy captures unsafe behaviors in human-bot dialogue settings with rich context-sensitive unsafe examples.

RNN Architecture Learning with Sparse Regularization (D19-1)

Copied to clipboard

Jesse Dodge, Roy Schwartz, Hao Peng, Noah A. Smith

Challenge:	State-of-the-art NLP models require hundreds of millions and even billions of parameters to perform, which can lead to memory usage and increased runtime.
Approach:	They propose a structure learning method that uses group lasso to learn sparse, parameter-efficient NLP models by pruning more than 90% of the weights of rational RNNs.
Outcome:	The proposed method learns sparse, parameter-efficient models without sacrificing performance relative to parameter-rich baselines.

FewRel 2.0: Towards More Challenging Few-Shot Relation Classification (D19-1)

Copied to clipboard

Tianyu Gao, Xu Han, Hao Zhu, Zhiyuan Liu, Peng Li, Maosong Sun, Jie Zhou

LLMRouterBench: A Massive Benchmark and Unified Framework for LLM Routing (2026.findings-acl)

Challenge:	Few-shot domain adaptation and NOTA detection are two real-world challenges for few-shot relation classification models.
Approach:	They propose a task to investigate two aspects of few-shot relation classification models . they build upon the FewRel dataset by adding a new test set in a different domain .
Outcome:	The proposed task can evaluate few-shot domain adaptation and few- shot none-of-the-above detection on a new domain and NOTA relation choice.

Copied to clipboard

Hao Li, Yiqun Zhang, Zhaoyan Guo, Chenxu Wang, Shengji Tang, Qiaosheng Zhang, Yang Chen, Biqing Qi, Peng Ye, Lei Bai, Zhen Wang, Shuyue Hu

Challenge:	Large language model (LLM) routing assigns each query to the best suitable model from an ensemble.
Approach:	They introduce a large-scale benchmark and unified framework for LLM routing . they find that many routing methods exhibit similar performance under unified evaluation .
Outcome:	The proposed benchmark provides comprehensive metrics for both performance-oriented and performance-cost trade-off routing.

MAVEN-ERE: A Unified Large-scale Dataset for Event Coreference, Temporal, Causal, and Subevent Relation Extraction (2022.emnlp-main)

Copied to clipboard

Xiaozhi Wang, Yulin Chen, Ning Ding, Hao Peng, Zimu Wang, Yankai Lin, Xu Han, Lei Hou, Juanzi Li, Zhiyuan Liu, Peng Li, Jie Zhou

MixKVQ: Query-Aware Mixed-Precision KV Cache Quantization for Long-Context Reasoning (2026.acl-long)

Challenge:	Existing datasets only cover limited relation types at once, which prevents models from taking full advantage of relation interactions.
Approach:	They construct a large-scale human-annotated ERE dataset with improved annotation schemes to address these drawbacks.
Outcome:	The proposed dataset is larger than existing datasets of all the ERE tasks by at least an order of magnitude.

Copied to clipboard

Tao Zhang, Ziqian Zeng, Hao Peng, Huiping Zhuang, Cen Chen

LEDGER: Scaling Agentic Document Editing with Dependency-aware Graph Retrieval (2026.findings-acl)

Challenge:	Existing low-bit quantization methods often exhibit severe performance degradation on complex reasoning tasks.
Approach:	They propose a plug-and-play method that uses a key channel's intrinsic quantization difficulty and relevance to the query to identify and preserve critical key channels that need higher precision.
Outcome:	Experiments on complex reasoning datasets show that the proposed method outperforms low-bit methods at a substantially reduced memory footprint.

Copied to clipboard

Hang Wang, Utkarsh Garg, Reza Davari, Huitian Jiao, Hao Cheng, Baolin Peng, Si-Qing Chen, Tao Ge

Green & Sustainable NLP

Challenge:	Document editing requires full-context awareness of dependencies, but processing entire documents for each edit incurs prohibitive token costs and latency.
Approach:	a framework that constructs lightweight dependency graphs captures semantic relationships and structural hierarchies across document elements is proposed for agentic document editing . a scaLing agentic agentic framework is based on a dependency graph framework that captures dependencies and refactors function dependencies.
Outcome:	a new framework achieves 76 consistency versus 56 baseline while reducing token usage by 85 . the framework is based on a framework that captures semantic relationships and structural hierarchies across document elements . it can be used to improve document consistency, but it also reduces token costs and latency .

Multi-View Incongruity Learning for Multimodal Sarcasm Detection (2025.coling-main)

Copied to clipboard

Diandian Guo, Cong Cao, Fangfang Yuan, Yanbing Liu, Guangjie Zeng, Xiaoyan Yu, Hao Peng, Philip S. Yu

Sentiment Analysis

Challenge:	Existing methods for multimodal sarcasm detection rely on spurious correlations, demonstrating poor generalizability beyond training environments.
Approach:	They propose a method that integrates multimodal incongruities via contrastive learning for multimodal sarcasm detection by using three views to drive multi-view learning.
Outcome:	The proposed method outperforms existing methods on benchmark datasets and shows that it is more generalizable than existing methods.

Language Models Hallucinate, but May Excel at Fact Verification (2024.naacl-long)

Copied to clipboard

Jian Guan, Jesse Dodge, David Wadden, Minlie Huang, Hao Peng

Improving Influence-based Instruction Tuning Data Selection for Balanced Learning of Diverse Capabilities (2025.findings-emnlp)

Challenge:	Recent advances in large language models (LLMs) have produced non-factual outputs . however, current LLMs suffer from the hallucination issue .
Approach:	They propose to use instruction-tuned LLMs to generate factual outputs . they find that FLAN-T5-11B performs best as a fact verifier .
Outcome:	The proposed method outperforms more capable LLMs like GPT3.5 and ChatGPT in the human evaluation.

Copied to clipboard

Qirun Dai, Dylan Zhang, Jiaqi W. Ma, Hao Peng

ADELIE: Aligning Large Language Models on Information Extraction (2024.emnlp-main)

Challenge:	Influence-based methods show promise in achieving (1), but often struggle with (2) . data selection is often biased towards high-influence tasks, harming performance on them .
Approach:	They propose a Balanced and Influential Data Selection algorithm that normalizes influence scores of training data and iteratively chooses the training example with the highest influence on the most underrepresented task.
Outcome:	The proposed model outperforms both state-of-the-art influence-based methods and non-influence-based frameworks on seven benchmarks spanning five diverse capabilities.

Copied to clipboard

Yunjia Qi, Hao Peng, Xiaozhi Wang, Bin Xu, Lei Hou, Juanzi Li

FinRipple: Aligning Large Language Models with Financial Market for Event Ripple Effect Awareness (2025.findings-acl)

Challenge:	Large language models (LLMs) struggle to follow complex instructions of IE tasks due to not being aligned with humans.
Approach:	They propose an aligned large language moDEL that effectively solves various IE tasks including closed IE, open IE and on-demand IE.
Outcome:	The proposed model achieves state-of-the-art (SoTA) performance among open-source models.

Copied to clipboard

Yuanjian Xu, Jianing Hao, Kunsheng Tang, Jingnan Chen, Anxian Liu, Peng Liu, Guang Zhang

The Devil is in the Details: On the Pitfalls of Event Extraction Evaluation (2023.findings-acl)

Challenge:	Financial markets exhibit complex dynamics where localized events trigger ripple effects across entities.
Approach:	They propose a framework that empowers large language models to analyze ripple effects . they use financial theory-guided large-scale reinforcement learning to align LLMs with the market .
Outcome:	The proposed framework allows LLMs to analyze ripple effects through financial theory-guided large-scale reinforcement learning.

Copied to clipboard

Hao Peng, Xiaozhi Wang, Feng Yao, Kaisheng Zeng, Lei Hou, Juanzi Li, Zhiyuan Liu, Weixing Shen

Modeling Context With Linear Attention for Scalable Document-Level Translation (2022.findings-emnlp)

Challenge:	Event extraction (EE) is a fundamental information extraction task aimed at extracting events from plain texts.
Approach:	They propose to specify data preprocessing, standardize outputs, and provide pipeline evaluation results to avoid these pitfalls.
Outcome:	The results show that the evaluations are reliable and lack pipeline evaluations.

Copied to clipboard

Zhaofeng Wu, Hao Peng, Nikolaos Pappas, Noah A. Smith

HTCInfoMax: A Global Model for Hierarchical Text Classification via Information Maximization (2021.naacl-main)

Challenge:	Document-level machine translation models lack quadratic complexity in the sequence length due to their attention layers.
Approach:	They evaluate a recent linear attention model with a sentential gate to promote a recency inductive bias and compare it to open-source document translation.
Outcome:	The proposed model significantly improves translation quality on IWSLT 2015 and OpenSubtitles 2018 with similar or better BLEU scores.

Copied to clipboard

Zhongfen Deng, Hao Peng, Dongxiao He, Jianxin Li, Philip Yu

Finetuning Pretrained Transformers into RNNs (2021.emnlp-main)

Challenge:	Existing models for hierarchical text classification do not consider statistical constraint on label representations learned by structure encoder.
Approach:	They propose a new hierarchical text classification model called HTCInfoMax which incorporates two modules to improve the model's representations.
Outcome:	The proposed model can model the interaction between each text sample and its ground truth labels explicitly which filters out irrelevant information.

Copied to clipboard

Jungo Kasai, Hao Peng, Yizhe Zhang, Dani Yogatama, Gabriel Ilharco, Nikolaos Pappas, Yi Mao, Weizhu Chen, Noah A. Smith

StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large Language Models (2024.findings-acl)

Challenge:	Efficient transformers outperform recurrent neural networks in natural language generation, but this comes with significant computational cost and memory footprint during generation.
Approach:	They propose to convert a pretrained transformer into its efficient recurrent counterpart, improving efficiency while maintaining accuracy.
Outcome:	The proposed transformers outperform recurrent neural networks in natural language generation but come with significant computational and memory footprint during generation.

Copied to clipboard

Zhicheng Guo, Sijie Cheng, Hao Wang, Shihao Liang, Yujia Qin, Peng Li, Zhiyuan Liu, Maosong Sun, Yang Liu

Context Length Alone Hurts LLM Performance Despite Perfect Retrieval (2025.findings-emnlp)

Challenge:	Large Language Models (LLMs) have witnessed remarkable advancements in recent years, prompting the exploration of tool learning.
Approach:	They propose a virtual API server and stable evaluation system to assess the stability of large-scale real-time APIs.
Outcome:	The proposed benchmarks demonstrate the stability of the proposed system and its caching system.

Copied to clipboard

Yufeng Du, Minyang Tian, Srikanth Ronanki, Subendhu Rongali, Sravan Babu Bodapati, Aram Galstyan, Azton Wells, Roy Schwartz, Eliu A Huerta, Hao Peng

Information Retrieval

Challenge:	Large language models (LLMs) often fail to scale their performance on long-context tasks performance in line with the context lengths they support.
Approach:	They propose a model-agnostic mitigation strategy that transforms a long-context task into a short-concept one by prompting the model to recite the retrieved evidence before attempting to solve the problem.
Outcome:	The proposed model improves on a long-context task up to 4% on RULER.

Pre-training Distillation for Large Language Models: A Design Space Exploration (2025.acl-long)

Copied to clipboard

Hao Peng, Xin Lv, Yushi Bai, Zijun Yao, Jiajie Zhang, Lei Hou, Juanzi Li

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

Challenge:	Knowledge distillation (KD) aims to transfer knowledge from a large teacher model to a smaller student model for model compression.
Approach:	They extend knowledge distillation to the pre-training phase of large language models . they first conduct an experiment using a teacher LLM to distill a 1.9B student LLM .
Outcome:	The proposed model can be used to distill a 1.9B student model using a teacher LLM.

Copied to clipboard

Xingyao Wang, Hao Peng, Reyhaneh Jabbarvand, Heng Ji

Prompt Tuning for Unified Multimodal Pretrained Models (2023.findings-acl)

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

Copied to clipboard

Hao Yang, Junyang Lin, An Yang, Peng Wang, Chang Zhou

TORQUE: A Reading Comprehension Dataset of Temporal Ordering Questions (2020.emnlp-main)

Challenge:	Prompt tuning has demonstrated success in natural language pretraining and even vision pretraining.
Approach:	They propose to apply prompt tuning to a unified sequence-to-sequence pretrained model by adding a sequence of learnable embeddings to each layer and finetuning the pretrained models on downstream tasks.
Outcome:	The proposed method outperforms other parameter-efficient tuning methods on multimodal models and is robust against adversarial attacks.

Copied to clipboard

Qiang Ning, Hao Wu, Rujun Han, Nanyun Peng, Matt Gardner, Dan Roth

Machine Reading Comprehension

Challenge:	Current machine reading comprehension benchmarks have no questions that test temporal phenomena . a new study studies reading comprehension for temporal relations .
Approach:	They propose a reading comprehension benchmark built on news snippets and 21k human-generated questions querying temporal relationships.
Outcome:	The new reading comprehension benchmark TORQUE achieves an exact-match score of 51% on the test set . the benchmark is built on 3.2k news snippets with 21k human-generated questions .

A Meta-framework for Spatiotemporal Quantity Extraction from Text (2022.acl-long)

Copied to clipboard

Qiang Ning, Ben Zhou, Hao Wu, Haoruo Peng, Chuchu Fan, Matt Gardner

PaLM: A Hybrid Parser and Language Model (D19-1)

Challenge:	a meta-framework for news events that extracts quantities from text is proposed . a previous work on news events focused on extracting event mentions, attributes, and relationships .
Approach:	They propose a meta-framework for solving the NLP problem of spatiotemporal quantity extraction . they demonstrate the framework is general and extensible, and shareable crowdsourcing pipeline and baseline models are used .
Outcome:	The proposed framework is general and extensible, the authors say . it can extract quantity from news streams, quickly respond to emergencies, investigate incidents .

Copied to clipboard

Hao Peng, Roy Schwartz, Noah A. Smith

Tailor: Generating and Perturbing Text with Semantic Controls (2022.acl-long)

Challenge:	Recent language models have shown strong data-fitting performance, but do not explicitly encode any notion of structural information.
Approach:	They propose a hybrid parser and neural language model that adds an attention layer over text spans in the left context.
Outcome:	The proposed model outperforms baseline models on language modeling and provides syntactically-informed representations of the context.

Copied to clipboard

Alexis Ross, Tongshuang Wu, Hao Peng, Matthew Peters, Matt Gardner

Challenge:	Existing studies train task-specific generators, relying on training a model for every perturbation.
Approach:	They propose a semantically-controlled text generation system that modifies sentences to match target attributes.
Outcome:	The proposed system produces textual outputs conditioned on control codes derived from semantic representations.

ROSE: Robust Selective Fine-tuning for Pre-trained Language Models (2022.emnlp-main)

Copied to clipboard

Lan Jiang, Hao Zhou, Yankai Lin, Peng Li, Jie Zhou, Rui Jiang

Robustness in NLP

Challenge:	Recent studies have highlighted the lack of adversarial robustness in pre-trained models.
Approach:	They propose a fine-tuning approach that conducts selective updates when adapting pre-trained models to downstream tasks.
Outcome:	The proposed approach improves adversarial robustness on downstream tasks . it eliminates spurious updates, leading to flatter and wider optima than the conventional method .

Uncertainty Calibration for Tool-Using Language Agents (2024.findings-emnlp)

Copied to clipboard

Hao Liu, Zi-Yi Dou, Yixin Wang, Nanyun Peng, Yisong Yue

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

Challenge:	Language agents are increasingly used to perform tasks and interact with a variety of external tools to achieve specific, goal-oriented objectives.
Approach:	They propose a tool calibration tool called ProbeCal which recalibrates the internal probabilities of tool-using language agents to better reflect the actual effectiveness of tool.
Outcome:	The proposed model significantly improves off-the-shelf language models in tool-using applications.

Copied to clipboard

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

One2Set + Large Language Model: Best Partners for Keyphrase Generation (2024.emnlp-main)

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

Copied to clipboard

Liangying Shao, Liang Zhang, Minlong Peng, Guoqi Ma, Hao Yue, Mingming Sun, Jinsong Su

SEA: Low-Resource Safety Alignment for Multimodal Large Language Models via Synthetic Embeddings (2025.acl-long)

Challenge:	Existing selection methods make redundant selections, causing poor recall and accuracy.
Approach:	They propose a framework to generate keyphrases from a one2set-based model and an LLM as selector.
Outcome:	The proposed framework surpasses state-of-the-art models in absent keyphrase prediction.

Copied to clipboard

Weikai Lu, Hao Peng, Huiping Zhuang, Cen Chen, Ziqian Zeng

Multimodality

Challenge:	Existing low-resource security alignment methods struggle with the security risks posed by additional modalities.
Approach:	They propose to use multimodal datasets to enhance safety alignment but it is costly to construct these datasets.
Outcome:	Experiments on image, video, and audio-based MLLMs show that the proposed method can synthesize a high-quality embedding on a single RTX3090 GPU within 24 seconds.

Transparency Helps Reveal When Language Models Learn Meaning (2023.tacl-1)

Copied to clipboard

Zhaofeng Wu, William Merrill, Hao Peng, Iz Beltagy, Noah A. Smith

MAVEN-FACT: A Large-scale Event Factuality Detection Dataset (2024.findings-emnlp)

Challenge:	Existing language models are trained to optimize unsupervised objectives on text . despite their centrality, current models do not represent natural language semantics well .
Approach:	They show that autoregressive and masked language models learn to emulate semantic relations between expressions when context-dependent . they argue that a learner that has access to all Java code can never learn execution .
Outcome:	a new study shows that language models fail to represent natural language semantics well . the authors show that the model learning fails when denotations are changed to be context-dependent .

Copied to clipboard

Chunyang Li, Hao Peng, Xiaozhi Wang, Yunjia Qi, Lei Hou, Bin Xu, Juanzi Li

SolEval: Benchmarking Large Language Models for Repository-level Solidity Smart Contract Generation (2025.emnlp-main)

Challenge:	Event factuality detection is under-explored due to the lack of high-quality large-scale data . efd is a subfield of event understanding, which aims to determine the factuity of textual events.
Approach:	They propose a large-scale EFD dataset with factuality annotations of 112,276 events . they find that adopting event arguments and relations helps in event factuity detection .
Outcome:	The proposed dataset includes factuality annotations of 112,276 events . it is the largest EFD dataset and is challenging for fine-tuned models and large language models .

Copied to clipboard

Zhiyuan Peng, Xin Yin, Rui Qian, Peiqin Lin, YongKang Liu, Hao Zhang, Chenhao Ying, Yuan Luo

T-Know: a Knowledge Graph-based Question Answering and Infor-mation Retrieval System for Traditional Chinese Medicine (C18-2)

Challenge:	Existing methods focus on Python and Java, neglecting Solidity, the programming language for Ethereum smart contracts.
Approach:	They construct a repository-level benchmark for Solidity to evaluate the performance of LLMs on Ethereum.
Outcome:	The proposed benchmarks show that the best performing LLM achieves only 26.29% Pass@10, highlighting room for improvement in Solidity code generation.

Copied to clipboard

Ziqing Liu, Enwei Peng, Shixing Yan, Guozheng Li, Tianyong Hao

Structured Data in NLP

Challenge:	Traditional Chinese Medicine (TCM) is one of precious intangible cultural heritages of the Chinese nation.
Approach:	They propose to use authorized and anonymized clinical records, medicine clinical guidelines, teaching materials, classic medical books, academic publications, etc. as data resources to build a TCM knowledge graph.
Outcome:	The proposed system extracts triples from free texts to build a TCM knowledge graph.

Hierarchical Bi-Directional Self-Attention Networks for Paper Review Rating Recommendation (2020.coling-main)

Copied to clipboard

Zhongfen Deng, Hao Peng, Congying Xia, Jianxin Li, Lifang He, Philip Yu

Neeko: Leveraging Dynamic LoRA for Efficient Multi-Character Role-Playing Agent (2024.emnlp-main)

Challenge:	Existing methods for review rating prediction ignore hierarchies among data . paper review rating predictions are important for improving paper review process .
Approach:	They propose a Hierarchical bi-directional self-attention Network framework for paper review rating prediction and recommendation . they leverage hierarchical structure of paper reviews with three levels of encoders .
Outcome:	The proposed approach can be used to make an effective decision-making tool for the academic paper review process.

Copied to clipboard

Xiaoyan Yu, Tongxu Luo, Yifan Wei, Fangyu Lei, Yiming Huang, Hao Peng, Liehuang Zhu

Green & Sustainable NLP

Challenge:	Large Language Models (LLMs) have revolutionized open-domain dialogue agents but face challenges in multi-character role-playing (MCRP) scenarios.
Approach:	They propose a framework for efficient multi-character role-playing that employs a dynamic low-rank adapter strategy and distinct LoRA blocks for each character.
Outcome:	Neeko employs a dynamic low-rank adapter (LoRA) strategy, enabling it to adapt seamlessly to diverse characters.

Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems (2025.acl-long)

Copied to clipboard

Hao Peng, Yunjia Qi, Xiaozhi Wang, Zijun Yao, Bin Xu, Lei Hou, Juanzi Li

Challenge:	Existing reward models focus on human preferences, neglecting verifiable correctness signals.
Approach:	They propose a reward system that combines human preference rewards with verifiable correctness signals to provide reliable rewards.
Outcome:	The proposed reward agent significantly outperforms vanilla reward models on benchmarks and inference-time best-of-n searches on real-world tasks.

Rational Recurrences (D18-1)

Copied to clipboard

Hao Peng, Roy Schwartz, Sam Thomson, Noah A. Smith

Challenge:	Recent studies show that neural models lack strong intuitions . recent studies show connections between convolutional neural networks and weighted finite state automata (WFSAs)
Approach:	They show that some recurrent neural networks share a connection to weighted finite state automata (WFSAs) they define rational recurrences as recursive hidden state update functions . they propose to use these functions to write forward calculations of a finite set of WFSA's .
Outcome:	The proposed model outperforms two baselines on language modeling and text classification.

Learning from Context or Names? An Empirical Study on Neural Relation Extraction (2020.emnlp-main)

Copied to clipboard

Hao Peng, Tianyu Gao, Xu Han, Yankai Lin, Peng Li, Zhiyuan Liu, Maosong Sun, Jie Zhou

MMD-ERE: Multi-Agent Multi-Sided Debate for Event Relation Extraction (2025.coling-main)

Challenge:	Existing datasets may leak shallow heuristics via entity mentions, thus contributing to the high performance on RE benchmarks.
Approach:	They propose an entity-masked contrastive framework for relation extraction to gain a deeper understanding on textual context and type information while avoiding rote memorization of entities.
Outcome:	The proposed framework improves the effectiveness and robustness of neural models in different RE scenarios.

Copied to clipboard

Yong Guan, Hao Peng, Lei Hou, Juanzi Li

Activation-Guided Local Editing for Jailbreaking Attacks (2026.acl-long)

Challenge:	Existing research indicates that LLMs can be overconfident and stubborn.
Approach:	They propose a multi-agent multi-sided debate approach for event relation extraction which explores the understanding of event relations between different participants before and after the debate.
Outcome:	The proposed approach outperforms established baselines on various ERE tasks and LLMs.

Copied to clipboard

Jiecong Wang, Haoran Li, Hao Peng, Ziqian Zeng, Zihao Wang, Haohua Du, Zhengtao Yu

Robustness in NLP

Challenge:	Existing methods for jailbreaking Large Language Models (LLMs) are limited and produce incoherent or unreadable inputs.
Approach:	They propose a two-stage framework that performs a one-shot, scenario-based generation of context and rephrases the original malicious query to obscure its harmful intent.
Outcome:	The proposed framework achieves state-of-the-art Attack Success Rate, with gains of up to 37.74% over the strongest baseline, and excellent transferability to black-box and large-scale models.

ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding (2022.findings-emnlp)

Copied to clipboard

Qiming Peng, Yinxu Pan, Wenjin Wang, Bin Luo, Zhenyu Zhang, Zhengjie Huang, Yuhui Cao, Weichong Yin, Yongfeng Chen, Yin Zhang, Shikun Feng, Yu Sun, Hao Tian, Hua Wu, Haifeng Wang

A Sequential Flow Control Framework for Multi-hop Knowledge Base Question Answering (2022.emnlp-main)

Challenge:	Existing methods for visually rich document understanding lack layout-centered knowledge . experimental results show that ERNIE-Layout improves layout awareness .
Approach:	They propose a document pre-training solution with layout knowledge enhancement in the whole workflow to learn better representations that combine the features from text, layout, and image.
Outcome:	The proposed model outperforms existing models on key downstream tasks.

Copied to clipboard

Minghui Xie, Chuzhan Hao, Peng Zhang