Papers by Wenpeng Yin

Event Linking: Grounding Event Mentions to Wikipedia (2023.eacl-main)

Challenge:	0Shot-TC is a challenging NLU problem to which little attention has been paid by the research community.
Approach:	They propose to use a standardized evaluation system to classify text snippets without seeing task specific training data.
Outcome:	The proposed model is based on a set of standardized evaluations and state-of-the-art baselines.

Copied to clipboard

Xiaodong Yu, Wenpeng Yin, Nitish Gupta, Dan Roth

Challenge:	a new task for natural language understanding is called Event Linking . the context where an event is mentioned lacks the details of this event .
Approach:	They propose a new task to link an article's event mention to the most appropriate Wikipedia page . they collect a training set from Wikipedia and evaluate two models to test the task .
Outcome:	The proposed model is based on a dataset and a real-world news domain . it is expected that the most appropriate Wikipedia page will provide rich knowledge about the mention .

DocNLI: A Large-scale Dataset for Document-level Natural Language Inference (2021.findings-acl)

Copied to clipboard

Wenpeng Yin, Dragomir Radev, Caiming Xiong

BatchMixup: Improving Training by Interpolating Hidden States of the Entire Mini-batch (2021.findings-acl)

Challenge:	Existing studies focus on sentence-level inference, which limits its application in downstream NLP problems.
Approach:	They propose to construct a large-scale dataset for document-level NLI that can be used to study NLP problems.
Outcome:	The proposed model performs well on popular sentence-level benchmarks and generalizes well to out-of-domain NLP tasks that rely on inference at document granularity.

Copied to clipboard

Wenpeng Yin, Huan Wang, Jin Qu, Caiming Xiong

Exploring Language Model Generalization in Low-Resource Extractive QA (2025.coling-main)

Challenge:	a data augmentation technique is used to augment data, but it has two drawbacks.
Approach:	They propose a new mixup paradigm that generates new points scattered throughout the whole mini-batch.
Outcome:	The proposed model improves the performance of NLP tasks while using different ratios of training data.

Copied to clipboard

Saptarshi Sengupta, Wenpeng Yin, Preslav Nakov, Shreya Ghosh, Suhang Wang

Pairwise Representation Learning for Event Coreference (2022.starsem-1)

Challenge:	Existing LLMs struggle with dataset demands of closed domains such as medicine and law . current LLM performance in closed domain is lacking, even on traditional tasks such as Natural Language Inference .
Approach:	They investigate Extractive Question Answering (EQA) with Large Language Models (LLMs) under domain drift . they find that LLMs struggle with dataset demands of closed domains .
Outcome:	The proposed model performs poorly in extractive question answering tasks under domain drift . the proposed model can generalize to domains that require specific knowledge without training .

Copied to clipboard

Xiaodong Yu, Wenpeng Yin, Dan Roth

TwoWingOS: A Two-Wing Optimization Strategy for Evidential Claim Verification (D18-1)

Challenge:	Existing work induces mention representations independently by extracting features from the sentence that contains the mention, without using the context of the other mention.
Approach:	They propose a Pairwise Representation Learning scheme for the event mention pairs that jointly encodes a pair of text snippets so that the representation of each mention in the pair is induced in the context of the other one.
Outcome:	The proposed scheme outperforms state-of-the-art representations on cross-document and within-document benchmarks.

Copied to clipboard

Wenpeng Yin, Dan Roth

Reasoning

Challenge:	Existing methods to determine whether a claim is supported by evidence are decoupled from determining the truth value of the claim.
Approach:	They propose a system that decouples evidence finding from determining the truth value of a claim . they propose identifying appropriate evidence for a given claim and determining its truth value .
Outcome:	The proposed system decouples evidence finding from determining the truth value of a claim . it can identify evidence candidates and determine the truth of the claim based on predicted evidence .

End-Task Oriented Textual Entailment via Deep Explorations of Inter-Sentence Interactions (P18-2)

Copied to clipboard

Wenpeng Yin, Dan Roth, Hinrich Schütze

Natural Language Interfaces

Challenge:	Existing datasets for textual entailment (TE) have been used to study TE.
Approach:	They propose a deep explorations of inter-sentence interactions for textual entailment task that uses a convolution to make important words in P and H play a dominant role in learnt representations.
Outcome:	Experiments show that the pretrained DEISTE on SciTail gets 5% improvement over prior state of the art and that it generalizes well on RTE-5.

LLM-driven Instruction Following: Progresses and Concerns (2023.emnlp-tutorial)

Copied to clipboard

Wenpeng Yin, Qinyuan Ye, Pengfei Liu, Xiang Ren, Hinrich Schütze

Challenge:	a tutorial on task instruction is aimed at researchers and practitioners interested in NLP generalization . labeled examples are unlikely to be available in large numbers or do not exist .
Approach:	This tutorial will examine the progress of natural language processing (NLP) using labeled examples. authors propose that task instructions act as a novel resource for supervision.
Outcome:	This tutorial aims to answer questions about instruction-driven NLP . it focuses on the use of task instructions in a low-shot scenario .

Toward Zero-Shot Instruction Following (2024.eacl-srw)

Copied to clipboard

Renze Lou, Wenpeng Yin

Advancing Language Models through Instruction Tuning: Recent Progress and Challenges (2025.emnlp-tutorials)

Challenge:	a novel approach to zero-shot cross-task generalization is proposed . prior work relied on demonstrations, but this approach could be overestimated .
Approach:	They propose a "demonstration-driven instruction following" setting for zero-shot cross-task generalization . they propose to automatically find out critical sentences in a paragraph-style task definition .
Outcome:	The proposed approach yields state-of-the-art performance on the Super-NaturalInstructions.

Copied to clipboard

Zhihan Zhang, Renze Lou, Fangkai Jiao, Wenpeng Yin, Meng Jiang

Recurrent One-Hop Predictions for Reasoning over Knowledge Graphs (C18-1)

Challenge:	tutorial addresses three critical questions within the field of instruction tuning: (1) What are the current focal points in instruction tuning research? (2) What are best practices in training an instruction-following model? (3) What new challenges have emerged?
Approach:	This tutorial presents a systematic overview of recent advances in instruction tuning.
Outcome:	The tutorial covers different stages in model training: supervised fine-tuning, preference optimization, and reinforcement learning.

Copied to clipboard

Wenpeng Yin, Yadollah Yaghoobzadeh, Hinrich Schütze

Structured Data in NLP

Challenge:	Large scale knowledge graphs (KGs) such as Freebase are generally incomplete.
Approach:	They propose a model that predicts entities at each step of mh-KB paths . the model is based on recurrent neural networks and vector representations of entities and relations .
Outcome:	The proposed models show state-of-the-art for two important multi-hop KG reasoning tasks.

Robustness of Learning from Task Instructions (2023.findings-acl)

Copied to clipboard

Jiasheng Gu, Hongyu Zhao, Hanzi Xu, Liangyu Nie, Hongyuan Mei, Wenpeng Yin

Robustness in NLP

Challenge:	traditional supervised learning mostly works on individual tasks and requires training on a large set of task-specific examples.
Approach:	a new study investigates the system robustness when instructions are manipulated and paraphrased . task instructions give the model the definition of the task and allow it to output the appropriate answer .
Outcome:	a new study shows that supervised learning is robust when instructions are manipulated, paraphrased or iii from different levels of conciseness.

Mixup-Transformer: Dynamic Data Augmentation for NLP Tasks (2020.coling-main)

Copied to clipboard

Lichao Sun, Congying Xia, Wenpeng Yin, Tingting Liang, Philip Yu, Lifang He

Enhancing LLM Capabilities Beyond Scaling Up (2024.emnlp-tutorials)

Challenge:	Recent work on data augmentation techniques that interpolate inputs and labels shows strong effectiveness in image classification.
Approach:	They propose to integrate mixup to transformer-based pre-trained architecture for NLP tasks while keeping the whole end-to-end training system.
Outcome:	The proposed framework improves on GLUEbenchmark and transformer-based learning models while keeping the whole end-to-end training system.

Copied to clipboard

Wenpeng Yin, Muhao Chen, Rui Zhang, Ben Zhou, Fei Wang, Dan Roth

FOFO: A Benchmark to Evaluate LLMs’ Format-Following Capability (2024.acl-long)

Challenge:	general-purpose large language models (LLMs) are expanding in scale and access to unpublic training data.
Approach:	This tutorial aims to examine the capabilities of general-purpose large language models . authors discuss adaptation of LLMs to address conflicts, defense against attacks .
Outcome:	This tutorial aims to examine the evolution of general-purpose large language models (LLMs) the authors argue that the evolution is dependent on the availability of training data and the scale of the models.

Copied to clipboard

Congying Xia, Chen Xing, Jiangshu Du, Xinyi Yang, Yihao Feng, Ran Xu, Wenpeng Yin, Caiming Xiong

Challenge:	Existing benchmarks fail to assess large language models’ format-following proficiency adequately.
Approach:	They propose a benchmark to evaluate large language models' ability to follow complex, domain-specific formats.
Outcome:	The proposed framework evaluates large language models' ability to follow complex, domain-specific formats across open-source and closed-source models.

Ultra-fine Entity Typing with Indirect Supervision from Natural Language Inference (2022.tacl-1)

Copied to clipboard

Bangzheng Li, Wenpeng Yin, Muhao Chen

Universal Natural Language Processing with Limited Annotations: Try Few-shot Textual Entailment as a Start (2020.emnlp-main)

Challenge:	Existing methods for ultra-fine entity typing fail to capture type semantics because of the large number of types and the scarcity of data per type.
Approach:	They propose a method that formulates entity typing as a natural language inference problem . they use indirect supervision from NLI to infer type information as textual hypotheses .
Outcome:	The proposed method achieves state-of-the-art performance on the ultra-fine entity typing task with limited training data.

Copied to clipboard

Wenpeng Yin, Nazneen Fatema Rajani, Dragomir Radev, Richard Socher, Caiming Xiong

X-Shot: A Unified System to Handle Frequent, Few-shot and Zero-shot Learning Simultaneously in Classification (2024.findings-acl)

Challenge:	a current approach to solving NLP problems is to build a problem-specific dataset . current approaches do not allow for transforming tasks into textual entailment .
Approach:	They propose a pretrained textual entailment system that can generalize across domains . they argue that when is it worth transforming an NLP task into textual detailment?
Outcome:	The proposed model can generalize across domains with few examples, the authors argue . they show that it can be used for several downstream NLP tasks with limited annotations .

Copied to clipboard

Hanzi Xu, Muhao Chen, Lifu Huang, Slobodan Vucetic, Wenpeng Yin

Unified Low-Resource Sequence Labeling by Sample-Aware Dynamic Sparse Finetuning (2023.emnlp-main)

Challenge:	Recent studies have focused on few-shot and zero-shot learning, but label occurrences vary widely . authors propose a new classification challenge that can be used to manage labels across the full frequency spectrum .
Approach:	They propose a new classification challenge that allows for label co-occurrences without predefined limits.
Outcome:	The proposed system can handle freq-shot, few-shot and zero-shot labels without limits.

Copied to clipboard

Sarkar Snigdha Sarathi Das, Haoran Zhang, Peng Shi, Wenpeng Yin, Rui Zhang

Efficient PRM Training Data Synthesis via Formal Verification (2026.findings-acl)

Challenge:	Named Entity Recognition, Relation Extraction, Semantic Role Labeling are examples of sequence labeling problems that require finetuning to the target format.
Approach:	They propose a dynamic sparse finetuning strategy that selectively focuses on a fraction of parameters, informed by feedback from highly regressing examples.
Outcome:	The proposed approach improves performance in low-resource settings and in extreme low-level settings.

Copied to clipboard

Ryo Kamoi, Yusen Zhang, Nan Zhang, Sarkar Snigdha Sarathi Das, Ranran Haoran Zhang, Wenpeng Yin, Rui Zhang

Responsible & Trustworthy NLP

Challenge:	Existing approaches for constructing PRM training data rely on human annotation or sampling-based labeling methods that require repeated LLM calls.
Approach:	They propose a framework that synthesizes PRM training data by annotating step-level error labels using formal verification tools such as Z3 and Isabelle.
Outcome:	The proposed framework synthesizes PRM training data from formal logic and theorem proving tasks without human annotation or additional LLM calls.

Contrastive Instruction Tuning (2024.findings-acl)

Copied to clipboard

Tianyi Yan, Fei Wang, James Y. Huang, Wenxuan Zhou, Fan Yin, Aram Galstyan, Wenpeng Yin, Muhao Chen

Responsible & Trustworthy NLP

Challenge:	Current LLMs exhibit limited robustness to unseen instructions, generating inconsistent outputs when the same instruction is phrased with slightly varied forms or language styles.
Approach:	They propose a method which maximizes the similarity between the hidden representations of semantically equivalent instruction-instance pairs while minimizing the similarities between semantically different ones.
Outcome:	Experiments on the PromptBench benchmark show that Contrastive Instruction Tuning improves LLMs’ robustness to unseen instructions with variations across character, word, sentence, and semantic levels by +2.5% in accuracy.

Multimodal Instruction Tuning with Conditional Mixture of LoRA (2024.acl-long)

Copied to clipboard

Ying Shen, Zhiyang Xu, Qifan Wang, Yu Cheng, Wenpeng Yin, Lifu Huang

Navigating the Dual Facets: A Comprehensive Evaluation of Sequential Memory Editing in Large Language Models (2024.acl-long)

Challenge:	Multimodal Large Language Models (MLLMs) have demonstrated proficiency in diverse tasks across different domains.
Approach:	They propose a method that integrates multimodal instruction tuning with Conditional Mixture-of-LoRA.
Outcome:	Experimental results show that MixLoRA outperforms LoRA with the same or higher ranks . MLLMs have demonstrated remarkable proficiency in diverse tasks across domains .

Copied to clipboard

Zihao Lin, Mohammad Beigi, Hongxuan Li, Yufan Zhou, Yuxiang Zhang, Qifan Wang, Wenpeng Yin, Lifu Huang

ConTinTin: Continual Learning from Task Instructions (2022.acl-long)

Challenge:	Memory Editing (ME) has emerged as an efficient method to modify erroneous facts or inject new knowledge into Large Language Models (LLMs).
Approach:	They propose to evaluate LLMs with single edit only and parameter-modifying ME with parameter-preserving ME.
Outcome:	The proposed method can maintain LLMs’ fundamental capabilities but struggles to accurately recall edited knowledge presented in a different format.

Copied to clipboard

Wenpeng Yin, Jia Li, Caiming Xiong

Challenge:	a new learning paradigm is proposed for NLP, which seeks supervision for solving a target task.
Approach:	They propose a new learning paradigm that uses textual instructions to learn new tasks . the main goal of machine learning algorithms lies in seeking supervision for solving a target task.
Outcome:	The proposed learning paradigm is based on a stream of more than 60 tasks . it makes full use of task instructions to improve forward-transfer and backward-transference .

Reference-Free Schema Generation for Literature Review Tables via Multi-Faceted Rewards (2026.acl-srw)

Copied to clipboard

Sinjoy Saha, Suman Saha, Mahfuza Farooque, Wenpeng Yin

Multimodality

Challenge:	Literature review systems generate literature review tables by inferring schemas and values from documents.
Approach:	They propose to use schema generation as a reinforcement learning problem to determine which dimensions to compare a set of papers.
Outcome:	The proposed model improves over the untuned model across intrinsic, reference-based, and LLM-judge metrics and remains competitive with supervised fine-tune models at 5 the parameter count on structural and diversity dimensions.

Can Large Language Models Adequately Perform Symbolic Reasoning Over Time Series? (2026.findings-acl)

Copied to clipboard

Zewen Liu, Juntong Ni, Xianfeng Tang, Max SY Lau, Qi He, Wenpeng Yin, Wei Jin

Seeing Things from a Different Angle:Discovering Diverse Perspectives about Claims (N19-1)

Challenge:	Large Language Models (LLMs) and Multimodal LLMs (MLLMs) show strong performance in complex reasoning tasks, but their ability to extract symbolic laws from time series data remains underexplored.
Approach:	They propose a benchmark to assess symbolic reasoning over real-world time series across three tasks: multivariate symbolic regression, Boolean network inference, and causal discovery.
Outcome:	The proposed framework integrates LLMs with genetic programming to form a closed-loop symbolic reasoning system.

Copied to clipboard

Sihao Chen, Daniel Khashabi, Wenpeng Yin, Chris Callison-Burch, Dan Roth

Reasoning

Challenge:	a number of fact checking techniques are used to identify and eliminate biases in text data.
Approach:	They propose to use search engines to expand and diversify a dataset of claims, perspectives and evidence to address a selection bias.
Outcome:	The proposed approach outperforms existing methods in a language understanding task.

Incremental Few-shot Text Classification with Multi-round New Classes: Formulation, Dataset and System (2021.naacl-main)

Copied to clipboard

Congying Xia, Wenpeng Yin, Yihao Feng, Philip Yu

Low-Resource NLP

Challenge:	Text classification is usually studied by labeling texts with relevant categories from a predefined set.
Approach:	They propose a task where a system incrementally handles multiple rounds of new classes . they propose two entailment approaches, ENTAILMENT and HYBRID, which show promise .
Outcome:	The proposed task is based on a few-shot text classification task in the NLP domain.

Large Language Models for Mathematical Reasoning: Progresses and Challenges (2024.eacl-srw)

Copied to clipboard

Janice Ahn, Rishu Verma, Renze Lou, Di Liu, Rui Zhang, Wenpeng Yin

Reasoning

Challenge:	a survey examines the landscape of mathematical problem-solving techniques . large language models have proven to be potent assets in unraveling nuances of mathematical reasoning .
Approach:	They examine the evolution of Large Language Models (LLMs) for solving mathematical problems . they examine the spectrum of LLM-oriented techniques proposed for solving math problems - and their challenges .
Outcome:	The survey examines the spectrum of proposed LLM-oriented techniques in solving math problems.

Learning to Synthesize Data for Semantic Parsing (2021.naacl-main)

Copied to clipboard

Bailin Wang, Wenpeng Yin, Xi Victoria Lin, Caiming Xiong

Anti-Overestimation Dialogue Policy Learning for Task-Completion Dialogue System (2022.findings-naacl)

Challenge:	Existing methods for synthesizing data for semantic parsing require handcrafted rules to synthesize new programs or utterance-program pairs.
Approach:	They propose to use a (non-neural) PCFG to model the composition of programs and a BART-based translation model to map a program to an utterance to learn a generative model from existing data.
Outcome:	The proposed model can be efficiently learned from existing data on benchmarks of GeoQuery and Spider.

Copied to clipboard

Chang Tian, Wenpeng Yin, Marie-Francine Moens

Dialogue Systems & Conversational Agents

Challenge:	Recent research has focused on reinforcement learning (RL)-based dialogue policy.
Approach:	They propose a dynamic partial average estimator (DPAV) of the ground truth maximum action value to solve the overestimation problem.
Outcome:	The proposed method achieves better results on three dialogue datasets with a lower computational load compared to baselines on three different domains with lower bias.

A Generic Method for Fine-grained Category Discovery in Natural Language Texts (2024.emnlp-main)

Copied to clipboard

Chang Tian, Matthew Blaschko, Wenpeng Yin, Mingzhe Xing, Yinliang Yue, Marie-Francine Moens