Papers by Tianyi Li

Context-Tuning: Learning Contextualized Prompts for Natural Language Generation (2022.coling-1)

Challenge:	Existing methods to predict scientific claims’ replicability use only hand-extracted statistics features without utilizing research papers’ text information.
Approach:	They propose two weakly supervised learning approaches that use automatically extracted text information of research papers to improve the prediction accuracy of research replication using both labeled and unlabeled datasets.
Outcome:	The proposed methods achieve an accuracy of 75.76% over real-world datasets.

Copied to clipboard

Tianyi Tang, Junyi Li, Wayne Xin Zhao, Ji-Rong Wen

Schoenfeld’s Anatomy of Mathematical Reasoning by Language Models (2026.acl-long)

Challenge:	Recent studies have shown that pretrained language models (PLMs) lack sufficient consideration of input semantics to generate natural language.
Approach:	They propose a continuous prompting approach to fine-tune PLMs for natural language generation by modeling an inverse generation process from output to input.
Outcome:	The proposed method fine-tunes only 0.12% of the parameters while maintaining good performance.

Copied to clipboard

Ming Li, Chenrui Fan, Yize Cheng, Soheil Feizi, Tianyi Zhou

Neutralizing Bias in LLM Reasoning using Entailment Graphs (2025.findings-acl)

Challenge:	Large language models expose reasoning traces, yet their underlying cognitive structure and steps remain difficult to identify and analyze beyond surface-level statistics.
Approach:	They propose a framework that explicitly abstracts reasoning traces into functional reasoning steps such as Analysis, Explore, Implement, Verify, etc.
Outcome:	The proposed framework reveals reproducible thinking dynamics and structural differences between reasoning and non-reasoning models, which are not apparent from token-level views.

Copied to clipboard

Liang Cheng, Tianyi Li, Zhaowei Wang, Tianyang Liu, Mark Steedman

Sources of Hallucination by Large Language Models on Inference Tasks (2023.findings-emnlp)

Challenge:	Natural Language Inference (NLI) is a foundational understanding task in language understanding.
Approach:	They propose a framework to construct counterfactual reasoning data and fine-tune LLMs to reduce attestation bias.
Outcome:	The proposed framework reduces hallucinations from attestation bias on original and bias-neutralized datasets while keeping hypotheses unchanged.

Copied to clipboard

Nick McKenna, Tianyi Li, Liang Cheng, Mohammad Hosseini, Mark Johnson, Mark Steedman

Sparser Mixture-of-Adapters with Cross-Layer Generalization (2025.naacl-long)

Challenge:	Large Language Models (LLMs) are claimed to be capable of Natural Language Inference (NLI)
Approach:	They propose to use LLMs to probe their behavior using controlled experiments.
Outcome:	The proposed models perform significantly worse on NLI test samples which do not conform to these biases than those which do.

Copied to clipboard

Ziyue Li, Tianyi Zhou

Green & Sustainable NLP

Challenge:	Existing methods for training large language models do not allow sharing adapters across layers . existing methods do not support sharing adapter pools, leading to redundancy and poor generalization .
Approach:	They propose a mixture-of-adapter framework that trains a pool of lightweight adapters at each layer and selects the most suitable ones for each input.
Outcome:	The proposed framework reduces active adapters by over 85% while boosting task accuracy.

Aligning Large Language Models with Implicit Preferences from User-Generated Content (2025.acl-long)

Copied to clipboard

Zhaoxuan Tan, Zheng Li, Tianyi Liu, Haodong Wang, Hyokun Yun, Ming Zeng, Pei Chen, Zhihan Zhang, Yifan Gao, Ruijie Wang, Priyanka Nigam, Bing Yin, Meng Jiang

1+1>2: Can Large Language Models Serve as Cross-Lingual Knowledge Aggregators? (2024.emnlp-main)

Challenge:	Existing preference learning methods rely heavily on curated data from humans or advanced LLMs, which is costly and difficult to scale.
Approach:	They propose a framework that leverages implicit preferences in unlabeled user-generated content to generate preference data.
Outcome:	The proposed framework transforms user-generated content into user queries and generates responses from the policy model.

Copied to clipboard

Yue Huang, Chenrui Fan, Yuan Li, Siyuan Wu, Tianyi Zhou, Xiangliang Zhang, Lichao Sun

DNN-driven Gradual Machine Learning for Aspect-term Sentiment Analysis (2021.findings-acl)

Challenge:	Large Language Models (LLMs) have been recognized for their impressive capabilities in natural language processing (NLP).
Approach:	They propose a method to enhance the multilingual performance of Large Language Models by aggregating knowledge from diverse languages.
Outcome:	The proposed method reduces the performance disparity across languages and offers valuable insights for further exploration.

Copied to clipboard

Murtadha Ahmed, Qun Chen, Yanyan Wang, Youcef Nafa, Zhanhuai Li, Tianyi Duan

Structured Data in NLP

Challenge:	Existing methods for Aspect-Term Sentiment Analysis (ATSA) use pre-specified lexicons to extract sentiment features.
Approach:	They propose a Deep Neural Network-driven approach for Aspect-Term Sentiment Analysis (ATSA) that leverages shared features between labeled and unlabeled instances for knowledge conveyance.
Outcome:	The proposed approach consistently achieves state-of-the-art performance on real benchmark data.

Align-then-Enhance: Multilingual Entailment Graph Enhancement with Soft Predicate Alignment (2023.findings-acl)

Copied to clipboard

Yuting Wu, Yutong Hu, Yansong Feng, Tianyi Li, Mark Steedman, Dongyan Zhao

Structured Data in NLP

Challenge:	Existing approaches to learn typed entailment graphs with predicates as nodes and enttailment relations as edges are incomplete.
Approach:	They propose a task to utilize entailment information from one EG to enhance another in a different language.
Outcome:	The proposed framework outperforms existing graphs in multilingual entailment graph enhancement tasks.

ALERT: An LLM-powered Benchmark for Automatic Evaluation of Recommendation Explanations (2025.naacl-long)

Copied to clipboard

Yichuan Li, Xinyang Zhang, Chenwei Zhang, Mao Li, Tianyi Liu, Pei Chen, Yifan Gao, Kyumin Lee, Kaize Ding, Zhengyang Wang, Zhihan Zhang, Jingbo Shang, Xian Li, Trishul Chilimbi

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

Challenge:	Existing benchmarks for recommendation explanation evaluation lack item diversity and user preferences data.
Approach:	They propose a model-agnostic recommendation explanation evaluation benchmark based on Amazon e-commerce categories with implicit preferences . they propose two novel automatic evaluators that enable scalable and human-preference aligned evaluation of explanations .
Outcome:	The proposed model-agnostic evaluation benchmark outperforms existing methods in a variety of domains.

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

AutoHallusion: Automatic Generation of Hallucination Benchmarks for Vision-Language Models (2024.findings-emnlp)

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

Xiyang Wu, Tianrui Guan, Dianqi Li, Shuaiyi Huang, Xiaoyu Liu, Xijun Wang, Ruiqi Xian, Abhinav Shrivastava, Furong Huang, Jordan Boyd-Graber, Tianyi Zhou, Dinesh Manocha

SPPO: Sequence-Level PPO for Long-Horizon Reasoning Tasks (2026.acl-long)

Challenge:	Large vision-language models are prone to hallucinations, where contextual cues in an image can trigger the language module to produce overconfident and incorrect reasoning about abnormal or hypothetical objects.
Approach:	They propose to automate the generation of hallucination-related questions using images . they propose to use three image manipulation strategies to induce hallucinosity .
Outcome:	The proposed approach reduces human bias in crafting such examples and improves accuracy.

Copied to clipboard

Tianyi Wang, Yixia Li, Long Li, Yibiao Chen, Shaohan Huang, Yun Chen, Peng Li, Yang Liu, Guanhua Chen

Do VLMs Have a Moral Backbone? A Study on the Fragile Morality of Vision-Language Models (2026.findings-acl)

Challenge:	Proximal Policy Optimization (PPO) is central to aligning Large Language Models with verifiable rewards.
Approach:	They propose a scalable algorithm that harmonizes sample efficiency with stability of outcome-based updates.
Outcome:	The proposed algorithm outperforms standard PPO and matches the performance of computation-heavy group-based methods.

Copied to clipboard

Zhining Liu, Tianyi Wang, Xiao Lin, Penghao Ouyang, Gaotang Li, Ze Yang, Hui Liu, Sumit Keswani, Vishwa Pardeshi, Huijun Zhao, Wei Fan, Hanghang Tong

MPID: A Modality-Preserving and Interaction-Driven Fusion Network for Multimodal Sentiment Analysis (2025.coling-main)

Challenge:	Vision-Language Models (VLMs) have advanced multimodal learning, driving progress in cross-modal reasoning.
Approach:	They propose to examine moral robustness of vision-language models by analyzing their moral stances under multimodal perturbations.
Outcome:	The proposed model-agnostic multimodal perturbations expose VLMs to a variety of moral vulnerabilities, including a sycophancy trade-off where stronger instruction-following models are more susceptible to persuasion.

Copied to clipboard

Tianyi Li, Daming Liu

Multimodality

Challenge:	Current methods for multimodal sensing analysis overlook nuanced differences and similarities across modalities, leading to potential biases.
Approach:	They propose a Modal-Preserving and Interaction-Driven Fusion Network to address these challenges by integrating text with audio and a separate Adaptive Graded Fusion Module for text and visual data.
Outcome:	The proposed model achieves state-of-the-art on CMU-MOSI, CMU -MOSEI, and CH-SIMS datasets.

TASA: Deceiving Question Answering Models by Twin Answer Sentences Attack (2022.emnlp-main)

Copied to clipboard

Yu Cao, Dianqi Li, Meng Fang, Tianyi Zhou, Jun Gao, Yibing Zhan, Dacheng Tao

Robustness in NLP

Challenge:	Existing adversarial models rely on keyword matching and ignore relevant contextual relations for answer prediction.
Approach:	They propose to use keyword matching to attack model with two biases that rely on a perturbed answer sentence and a distracting answer sentence to misguide model.
Outcome:	The proposed method produces fluent and grammatical adversarial contexts while maintaining gold answers.

Human-in-the-loop Schema Induction (2023.acl-demo)

Copied to clipboard

Tianyi Zhang, Isaac Tham, Zhaoyi Hou, Jiaxuan Ren, Leon Zhou, Hainiu Xu, Li Zhang, Lara Martin, Rotem Dror, Sha Li, Heng Ji, Martha Palmer, Susan Windisch Brown, Reece Suchocki, Chris Callison-Burch

Structured Data in NLP

Challenge:	Existing approaches to event-centric natural language understanding (NLU) have been limited to linear and temporal ones.
Approach:	They propose a human-in-the-loop schema induction system powered by GPT-3 . they show that it transfers to new domains more easily than previous approaches .
Outcome:	The proposed system transfers to new domains more easily than previous approaches and reduces human curation.

MVP: Multi-task Supervised Pre-training for Natural Language Generation (2023.findings-acl)

Copied to clipboard

Tianyi Tang, Junyi Li, Wayne Xin Zhao, Ji-Rong Wen

Low-Resource NLP

Challenge:	Pre-trained language models (PLMs) have achieved remarkable success in natural language generation tasks.
Approach:	They propose to use a large-scale natural language generation corpus to pre-train a text generation model MVP in a supervised manner.
Outcome:	The proposed model outperforms BART and Flan-T5 on 13 out of 17 datasets and outperformed BART by 9.3% and FlaN-T5.

Merging Experts into One: Improving Computational Efficiency of Mixture of Experts (2023.emnlp-main)

Copied to clipboard

Shwai He, Run-Ze Fan, Liang Ding, Li Shen, Tianyi Zhou, Dacheng Tao

Green & Sustainable NLP

Challenge:	Extensive experiments show that MEO significantly improves computational efficiency . compared to dense networks, sparsely activated networks only employ a few parameters for each input .
Approach:	They propose a method that merges multiple experts into one to reduce computation costs . they demonstrate that a sparse Mixture of Experts (MoE) can reduce the cost by activating a small subset of parameters for each input .
Outcome:	The proposed approach reduces the computational cost to that of a single expert by 83.3% compared to 82.6% in vanilla MoE.

TempLM: Distilling Language Models into Template-Based Generators (2023.findings-acl)

Copied to clipboard

Tianyi Zhang, Mina Lee, Xiang Lisa Li, Ende Shen, Tatsunori Hashimoto

Empirical Study on Data Attributes Insufficiency of Evaluation Benchmarks for LLMs (2025.coling-main)

Challenge:	Pretrained language models (PLMs) have greatly improved text generation, but they have also been known to produce unfaithful or inappropriate content.
Approach:	They propose a pretrained language model that is a template-based generator and uses it to generate a text.
Outcome:	The proposed model is more faithful than the original PLM and more fluent than prior template systems.

Copied to clipboard

Chuang Liu, Renren Jin, Zheng Yao, Tianyi Li, Liang Cheng, Mark Steedman, Deyi Xiong

Challenge:	Existing benchmarks for evaluating large language models neglect key qualitative data attributes that can significantly impact the final rankings of LLMs.
Approach:	They propose a framework with three modules designed to assess diversity, redundancy, and difficulty.
Outcome:	The proposed framework systematically incorporates diversity, redundancy, and difficulty attributes and shows that they influence the ranking of LLMs.

Improving Large Language Models Function Calling and Interpretability via Guided-Structured Templates (2025.emnlp-main)

Copied to clipboard

Hy Dang, Tianyi Liu, Zhuofeng Wu, Jingfeng Yang, Haoming Jiang, Tao Yang, Pei Chen, Zhengyang Wang, Helen Wang, Huasheng Li, Bing Yin, Meng Jiang

PLAWBENCH: A Rubric-Based Benchmark for Evaluating LLMs in Real-World Legal Practice (2026.acl-long)

Challenge:	Large language models (LLMs) have strong reasoning and tool-use capabilities, yet fail in real-world tool-interactions due to incorrect parameterization, poor tool selection, or misinterpretation of user intent.
Approach:	They propose a curriculum-inspired framework that leverages structured reasoning templates to guide LLMs through more deliberate step-by-step instructions for generating function calls.
Outcome:	The proposed framework reduces tool-use errors and improves interpretability and transparency of tool-using agents.

Copied to clipboard

Yuzhen Shi, Huanghai Liu, Yiran HU, Song Gaojie, Xu Xinran, Yubo Ma, Tianyi Tang, Li Zhang, Qingjing Chen, Feng Di, Wenbo Lv, Weiheng Wu, Kexin Yang, Sen Yang, Wei Wang, Rongyao Shi, Qiu Yuanyang, Yuemeng Qi, Zhang Jingwen, Sui Xiaoyu, Yifan Chen, Zhang Yi, An Yang, Bowen Yu, Dayiheng Liu, Junyang Lin, Weixing Shen, Bing Zhao, Charles L. A. Clarke, HU Wei

RuleR: Improving LLM Controllability by Rule-based Data Recycling (2025.naacl-short)

Challenge:	Existing benchmarks for large language models (LLMs) are coarse, single-dimensional metrics and do not explicitly assess fine-grained legal reasoning.
Approach:	They propose a Practical Law Benchmark to evaluate large language models in real-world legal practice scenarios.
Outcome:	The proposed model is based on 850 questions and 13 scenarios with expert-designed evaluation rubrics.

Copied to clipboard

Ming Li, Han Chen, Chenguang Wang, Dang Nguyen, Dianqi Li, Tianyi Zhou

Challenge:	Existing supervised fine-tuning datasets are composed of general instructions without userspecified constraints.
Approach:	They propose a data augmentation method incorporating multiple constraints into the original data samples according to predefined rules to create new training tasks.
Outcome:	The proposed method improves LLM controllability while maintaining general instruction-following capabilities.

NGQA: A Nutritional Graph Question Answering Benchmark for Personalized Health-aware Nutritional Reasoning (2025.acl-long)

Copied to clipboard

Zheyuan Zhang, Yiyang Li, Nhi Ha Lan Le, Zehong Wang, Tianyi Ma, Vincent Galassi, Keerthiram Murugesan, Nuno Moniz, Werner Geyer, Nitesh V Chawla, Chuxu Zhang, Yanfang Ye

Multimodality

Challenge:	Diet plays a critical role in human health, but tailoring dietary reasoning to individual health conditions remains a challenge.
Approach:	a new benchmark evaluates dietary reasoning using a national health survey data set.
Outcome:	The NGQA benchmark evaluates dietary reasoning across three tasks using a set of question complexity settings and baseline models.

Language Models Are Poor Learners of Directional Inference (2022.findings-emnlp)

Copied to clipboard

Tianyi Li, Mohammad Javad Hosseini, Sabine Weber, Mark Steedman

From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning (2024.naacl-long)

Challenge:	Existing datasets fail to test directionality and are infested by artefacts that can be learnt as proxy for entailments, yielding over-optimistic results.
Approach:	They propose a benchmark for directional predicate entailments that is extrinsic to existing training sets.
Outcome:	The proposed model is incompetent on directional predicate entailments, compared to engorgement graphs, but limited by sparsity.

Copied to clipboard

Ming Li, Yong Zhang, Zhitao Li, Jiuhai Chen, Lichang Chen, Ning Cheng, Jianzong Wang, Tianyi Zhou, Jing Xiao

Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning (2024.findings-acl)

Challenge:	Large Language Models (LLMs) have revolutionized the landscape of artificial intelligence.
Approach:	They propose a self-guided method to identify and select cherry samples from open-source datasets, minimizing manual curation and potential cost for instruction tuning an LLM.
Outcome:	The proposed method enables LLMs to identify discrepancies between expected responses and intrinsic generation capability, and a marked uptick in model training efficiency.

Copied to clipboard

Ming Li, Lichang Chen, Jiuhai Chen, Shwai He, Jiuxiang Gu, Tianyi Zhou

S2LPP: Small-to-Large Prompt Prediction across LLMs (2025.findings-emnlp)

Challenge:	Instruction tuning is critical to large language models but its success heavily relies on the training data quality.
Approach:	They propose a paradigm that synergizes a teacher LLM’s reflection and introspection with the data selection capability of the student LLM to automatically refine existing instruction-tuning data.
Outcome:	The proposed method achieves much stronger and top-tier 7B and 13B LLMs without collecting brand-new data.

Copied to clipboard

Liang Cheng, Tianyi Li, Zhaowei Wang, Mark Steedman

Explicit Inductive Inference using Large Language Models (2024.findings-emnlp)

Challenge:	a small model can be used to select effective prompt templates for a larger model.
Approach:	They propose a method to use a smaller model to select effective prompt templates for a larger model.
Outcome:	The proposed method significantly reduces the cost of prompt engineering while matching performance with optimal prompts among candidates.

Copied to clipboard

Tianyang Liu, Tianyi Li, Liang Cheng, Mark Steedman

How Instruction and Reasoning Data shape Post-Training: Data Quality through the Lens of Layer-wise Gradients (2026.acl-long)

Challenge:	Large Language Models (LLMs) suffer a signifi- cant performance drop when entailment labels disagree with the attestation label of hypothesis H.
Approach:	They propose a pipeline that exploits an LLM's attestation bias to do explicit inductive inference . they transform a premise into attested alternatives and aggregate the results .
Outcome:	The proposed pipeline improves the performance of large language models on inference tasks and alleviates the attestation bias.

Copied to clipboard

Ming Li, Yanhong Li, Ziyue Li, Tianyi Zhou

Mosaic-IT: Cost-Free Compositional Data Synthesis for Instruction Tuning (2025.findings-acl)

Challenge:	Spectral properties of low/high-quality instruction and reasoning data are used to explain finetuning dynamics in large language models.
Approach:	They propose to analyze layer-wise gradients induced by low/high-quality instruction and reasoning data for LLM post-training.
Outcome:	The results show that higher-quality data are associated with lower nuclear norms and higher effective ranks.

Copied to clipboard

Ming Li, Pei Chen, Chenguang Wang, Hongyu Zhao, Yijun Liang, YuPeng Hou, Fuxiao Liu, Tianyi Zhou

BAMBOO: A Comprehensive Benchmark for Evaluating Long Text Modeling Capacities of Large Language Models (2024.lrec-main)

Challenge:	Current instruction tuning relies on teacher models or human intervention to generate and refine the instructions and responses for training, which are costly, non-sustainable, and may lack diversity.
Approach:	They propose a human/model-free compositional data synthesis method that can create rich and diverse augmentations from existing instruction tuning data to enhance large language models.
Outcome:	The proposed method improves performance over benchmarks and reduces training costs by 80% compared with original instruction tuning.

Copied to clipboard

Zican Dong, Tianyi Tang, Junyi Li, Wayne Xin Zhao, Ji-Rong Wen

HALLUCANA: Fixing LLM Hallucination with A Canary Lookahead (2025.findings-naacl)

Challenge:	Existing long context models suffer from performance decline when the input text exceeds their length limit.
Approach:	They propose a multi-task long context benchmark to evaluate LLMs' long context ability using 10 datasets from 5 different NLP tasks.
Outcome:	The proposed model covers 5 domains and core capacities of large language models.

Copied to clipboard

Tianyi Li, Erenay Dayanik, Shubhi Tyagi, Andrea Pierleoni

Zero-shot Visual Question Answering with Language Model Feedback (2023.findings-acl)

Challenge:	Existing methods to detect factual hallucinations w.r.t. world knowledge require assistive generations (samples, drafts, etc.) Existing approaches to factuality hallucinism detection, such as SelfCheckGPT, require assistively generation (sequences, Drafts, and etc.). Existing studies on factualism hallucinosation detection require assistives generations (Sample, draft, etc).
Approach:	They propose a canary lookahead which detects and corrects factual hallucinations of Large Language Models in long-form generation by exploiting the internal factuality representation in the LLM hidden space.
Outcome:	The proposed method improves generation quality by 2.5x while consuming over 6 times less compute.

Copied to clipboard

Yifan Du, Junyi Li, Tianyi Tang, Wayne Xin Zhao, Ji-Rong Wen

Multimodality

Challenge:	Existing methods for knowledge-based visual question answering are based on pre-trained language models.
Approach:	They propose a language model guided captioning approach that leverages a pre-trained language model to generate captions for an image to help answer a visual question.
Outcome:	The proposed method outperforms several competing methods on the knowledge-based VQA task and achieves comparable results to a fine-tuned VLP model.

DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLMs Jailbreakers (2024.findings-emnlp)

Copied to clipboard

Xirui Li, Ruochen Wang, Minhao Cheng, Tianyi Zhou, Cho-Jui Hsieh

ATLAS: Agent Tuning via Learning Critical Steps (2025.findings-acl)

Challenge:	Existing jailbreaking methods view a malicious prompt as a whole but they are not effective at reducing LLMs’ attention on combinations of words with malice.
Approach:	They propose an automatic prompt Decomposition and Reconstruction framework for jailbreaking Attack that decomposes a malicious prompt into separate sub-prompts and reassembles them implicitly by In-Context Learning.
Outcome:	The proposed framework reduces LLMs' attention on malice words by presenting them to LLM in a fragmented form, addressing these limitations and improving attack effectiveness.

Copied to clipboard

Zhixun Chen, Ming Li, Yuxuan Huang, Yali Du, Meng Fang, Tianyi Zhou

PDDLEGO: Iterative Planning in Textual Environments (2024.starsem-1)

Challenge:	Existing agent tuning approaches employ supervised finetuning on entire expert trajectories, but behavior-cloning of full traitories introduces expert bias and weakens generalization to states not covered by the expert data.
Approach:	They propose a method that finetunes LLMs on critical steps in expert trajectories and identifies and finetuns them on these steps with reduced costs.
Outcome:	The proposed method outperforms existing methods and open-source LLM agents on only 30% critical steps in extensive experiments.

Copied to clipboard

Li Zhang, Peter Jansen, Tianyi Zhang, Peter Clark, Chris Callison-Burch, Niket Tandon

Challenge:	Existing methods to plan in textual environments rely on a fully-observed environment where all entity states are known, but are not interpretable.
Approach:	They propose to use LLMs to generate a formal representation of the environment that can be solved by a symbolic planner.
Outcome:	The proposed model outperforms existing methods in the Coin Collector simulation and Cooking World simulations.

Improving Long-Tail Relation Extraction with Collaborating Relation-Augmented Attention (2020.coling-main)

Copied to clipboard

Yang Li, Tao Shen, Guodong Long, Jing Jiang, Tianyi Zhou, Chengqi Zhang

Information Extraction & Text Mining

Challenge:	Existing approaches to handle wrong labeling and long-tail relations are labor-intensive and scarce training data.
Approach:	They propose a neural network to handle wrong labeling and long-tail relations by collaborating relation-augmented attention.
Outcome:	The proposed neural network improves the state-of-the-art on the NYT dataset .

Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning (2024.acl-long)

Copied to clipboard

Ming Li, Yong Zhang, Shwai He, Zhitao Li, Hongyu Zhao, Jianzong Wang, Ning Cheng, Tianyi Zhou

Learning to Transfer Prompts for Text Generation (2022.naacl-main)

Challenge:	Earlier studies of instruction tuning on Large Language Models focus on creating large, varied, and high-quality datasets with responses curated by human experts.
Approach:	They propose to use a smaller and weaker model to fine tune a larger and stronger model . they find it can largely speed up the data filtering and improve performance .
Outcome:	The proposed model can filter instruction data faster and better on benchmarks.

Copied to clipboard

Junyi Li, Tianyi Tang, Jian-Yun Nie, Ji-Rong Wen, Xin Zhao

TheraAgent: Self-Improving Therapeutic Agent for Precise and Comprehensive Treatment Planning (2026.findings-acl)

Challenge:	Pretrained language models (PLMs) have made remarkable progress in text generation tasks via fine-tuning.
Approach:	They propose a prompt-based method that learns source prompts and transfers them as target prompts to perform target generation tasks.
Outcome:	The proposed method can be used to perform text generation tasks in a transferable setting.

Copied to clipboard

Junkai Li, Yunghwei Lai, Tianyi Zhu, Zheng Long Lee, Weizhi Ma, Yang Liu

RASPberry: Retrieval-Augmented Monte Carlo Tree Self-Play with Reasoning Consistency for Multi-Hop Question Answering (2025.findings-acl)

Challenge:	Existing large language models rely on one-shot output without explicit verification, resulting in rough, incomplete, and potentially unsafe treatment plans.
Approach:	They propose an agentic framework that replaces one-shot generation with an iterative generate-judge-refine pipeline.
Outcome:	The proposed framework achieves state-of-the-art results on HealthBench, leading in Accuracy and Completeness.

Copied to clipboard

Baixuan Li, Yunlong Fan, Tianyi Ma, Miao Gao, Chuanqi Shi, Zhiqiang Gao

Cross-lingual Inference with A Chinese Entailment Graph (2022.findings-acl)

Challenge:	Existing methods for generating and analyzing multiple document knowledge are not effective for multi-hop question answering.
Approach:	They propose a Monte Carlo tree-based approach to inference-time scaling using RASPberry.
Outcome:	Experimental results show that the proposed method achieves better inference-time scaling on smaller LLMs.

Copied to clipboard

Tianyi Li, Sabine Weber, Mohammad Javad Hosseini, Liane Guillou, Mark Steedman

Understanding the Thinking Process of Reasoning Models: A Perspective from Schoenfeld’s Episode Theory (2025.emnlp-main)

Challenge:	Existing work on predicate entailment detection from typed open relation triples has not been able to detect predicates.
Approach:	They propose a pipeline for building Chinese entailment graphs using an open relation extraction method.
Outcome:	The proposed pipeline outperforms monolingual and Chinese entailment graphs on a parallel dataset.

Copied to clipboard

Ming Li, Nan Zhang, Chenrui Fan, Hong Jiao, Yanbin Fu, Sydney Peters, Qingshu Xu, Robert Lissitz, Tianyi Zhou

Linguistics & Cognitive NLP

Challenge:	Large Reasoning Models (LRMs) generate extensive chain-of-thought reasoning, but we lack a principled framework for understanding how these thoughts are structured.
Approach:	They propose a method to analyze the reasoning traces of Large Reasoning Models using Schoenfeld’s Episode Theory.
Outcome:	The proposed framework provides a theoretically grounded methodology for interpreting LRM cognition and enables future work on more controllable and transparent reasoning systems.

WinSpot: GUI Grounding Benchmark with Multimodal Large Language Models (2025.acl-short)

Copied to clipboard

Zheng Hui, Yinheng Li, Dan Zhao, Colby Banbury, Tianyi Chen, Kazuhito Koishida

RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment (2025.findings-acl)

Challenge:	Existing GUI grounding data focuses on web-based elements, leaving a gap in real-world GUI interaction data for non-web applications.
Approach:	They propose a framework that leverages Large Language Models to generate large-scale GUI grounding data.
Outcome:	The framework validates and refines 5,000 GUI coordinate-instruction pairs and provides high-quality data for training and evaluating visual GUI agents.

Copied to clipboard

Zhuoran Jin, Hongbang Yuan, Tianyi Men, Pengfei Cao, Yubo Chen, Jiexin Xu, Huaijun Li, Xiaojian Jiang, Kang Liu, Jun Zhao

Information Retrieval

Challenge:	Existing retrieval augmented language models often overlook effective alignment with human preferences.
Approach:	They propose a benchmark to evaluate RMs in retrieval augmented language models . they incorporate 18 RAG subsets, six retrievers, and 24 RALMs to increase diversity .
Outcome:	The proposed benchmark combines 18 RAG subsets, six retrievers, and 24 RALMs to increase diversity of data sources.

TextBox 2.0: A Text Generation Library with Pre-trained Language Models (2022.emnlp-demos)

Copied to clipboard

Tianyi Tang, Junyi Li, Zhipeng Chen, Yiwen Hu, Zhuohao Yu, Wenxun Dai, Wayne Xin Zhao, Jian-yun Nie, Ji-rong Wen

GUI Agents: A Survey (2025.findings-acl)

Challenge:	TextBox 2.0 focuses on the use of pre-trained language models (PLMs) to generate text.
Approach:	They propose a library that integrates pre-trained language models into 13 common text generation tasks and 83 datasets.
Outcome:	The proposed library covers 13 common text generation tasks and their corresponding datasets and incorporates 45 PLMs covering general, translation, Chinese, dialogue, controllable, distilled, prompting, and lightweight PLM.

Copied to clipboard

Dang Nguyen, Jian Chen, Yu Wang, Gang Wu, Namyong Park, Zhengmian Hu, Hanjia Lyu, Junda Wu, Ryan Aponte, Yu Xia, Xintong Li, Jing Shi, Hongjie Chen, Viet Dac Lai, Zhouhang Xie, Sungchul Kim, Ruiyi Zhang, Tong Yu, Mehrab Tanjim, Nesreen K. Ahmed, Puneet Mathur, Seunghyun Yoon, Lina Yao, Branislav Kveton, Jihyung Kil, Thien Huu Nguyen, Trung Bui, Tianyi Zhou, Ryan A. Rossi, Franck Dernoncourt

Challenge:	Large Foundation Models (LFMs) have transformed the landscape of AI research and day-to-day life.
Approach:	They propose a framework that delineates GUI agents' perception, reasoning, planning, and acting capabilities.
Outcome:	The proposed framework delineates their perception, reasoning, planning, and acting capabilities.

Can LLMs Estimate Student Struggles? Human-AI Difficulty Alignment with Proficiency Simulation for Item Difficulty Prediction (2026.findings-acl)

Copied to clipboard

Ming Li, Han Chen, Yunze Xiao, Jian Chen, Hong Jiao, Tianyi Zhou

Cognitive Modeling

Challenge:	Accurate estimation of item (question or task) difficulty suffers from the cold start problem.
Approach:	They propose to use large-scale empirical analysis to examine human-AI Difficulty Alignment . they find that models struggle to simulate the capability limitations of students .
Outcome:	The proposed model size is not reliably helpful for human-AI alignment . high performance often impedes accurate difficulty estimation, the authors say .

LLMBox: A Comprehensive Library for Large Language Models (2024.acl-demos)

Copied to clipboard

Tianyi Tang, Hu Yiwen, Bingqian Li, Wenyang Luo, ZiJing Qin, Haoxiang Sun, Jiapeng Wang, Shiyi Xu, Xiaoxue Cheng, Geyang Guo, Han Peng, Bowen Zheng, Yiru Tang, Yingqian Min, Yushuo Chen, Jie Chen, Ranchi Zhao, Luran Ding, Yuhao Wang, Zican Dong, Xia Chunxuan, Junyi Li, Kun Zhou, Xin Zhao, Ji-Rong Wen

A Usage-centric Take on Intent Understanding in E-Commerce (2024.emnlp-main)

Challenge:	a library to facilitate the development, use, and evaluation of large language models (LLMs) is presented.
Approach:	They propose a unified library to facilitate the development, use and evaluation of large language models (LLMs).
Outcome:	The proposed library is based on extensive experiments in a variety of evaluation settings.

Copied to clipboard

Wendi Zhou, Tianyi Li, Pavlos Vougiouklis, Mark Steedman, Jeff Pan

Challenge:	Identifying and understanding user intents is a crucial task for E-Commerce.
Approach:	They propose to use intent understanding as a natural language reasoning task independent of product ontologies to identify and understand user intents.
Outcome:	The proposed framework can't be used to strongly align user intents with products with desirable properties and recommend useful products across diverse categories.

Trait Activation in Silicon: A Situation-Aware Framework for Psychologically Grounded Role-Playing (2026.acl-long)

Copied to clipboard

Zuolong Li, Pingyu Wu, Xianwen Huang, Tianyi Wei, Wenbo Zhou

What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective (2025.acl-long)

Challenge:	Role-playing agents lack a deep understanding of complex human psychological mechanisms.
Approach:	They propose a situation-aware framework that decouples personality traits into bidirectional LoRA adapters.
Outcome:	Empirical results show that PD-LLM achieves superior performance in both static fidelity and dynamic adaptability.

Copied to clipboard

Ming Li, Yanhong Li, Tianyi Zhou

The Web Can Be Your Oyster for Improving Language Models (2023.findings-acl)

Challenge:	Xu et al., 2024) study shows that slow thinking can distinguish correct and irrelevant reasoning paths.
Approach:	They investigate how fast vs. slow thinking affects layer-wise gradients in large language models . they find that slow thinking can distinguish correct and irrelevant reasoning paths .
Outcome:	The results show that slow thinking can distinguish correct and irrelevant reasoning paths.

Copied to clipboard

Junyi Li, Tianyi Tang, Wayne Xin Zhao, Jingyuan Wang, Jian-Yun Nie, Ji-Rong Wen

Phrase-level Textual Adversarial Attack with Label Preservation (2022.findings-naacl)

Challenge:	Pretrained language models encode a large amount of knowledge, but knowledge is frozen at the time of training, and the models become static and limited by training data.
Approach:	They propose an adaptive search engine assisted learning method that can self-evaluate the confidence level of PLM’s predictions and adaptively determine when to refer to the web for more data.
Outcome:	The proposed model outperforms retrieval-augmented methods on 16 knowledge-intensive tasks on a wide range of knowledge-related tasks.

Copied to clipboard

Yibin Lei, Yu Cao, Dianqi Li, Tianyi Zhou, Meng Fang, Mykola Pechenizkiy

Robustness in NLP

Challenge:	Existing adversarial attacks are usually realized through word-level or sentence-level perturbations, which either limit the perturbation space or sacrifice fluency and textual quality.
Approach:	They propose a phrase-level perturbation-based adversarial ATtack that generates adversarials through phrase- level perturbations.
Outcome:	The proposed approach improves the performance of natural language processing models by reducing the need for word-level perturbations and preserving the fluency and grammaticality of the samples.

A Training-Free Length Extrapolation Approach for LLMs: Greedy Attention Logit Interpolation (2025.emnlp-main)

Copied to clipboard

Yan Li, Tianyi Zhang, Zechuan Li, Caren Han

Interactive Text-to-SQL Generation via Editable Step-by-Step Explanations (2023.emnlp-main)

Challenge:	Existing solutions to problem of positional out-of-distribution (O.O.D.) are inefficient, redundant, and lack local positional information.
Approach:	They propose a training-free method that greedily reuses pretrained positional intervals and interpolates attention logits to eliminate outliers.
Outcome:	The proposed method achieves stable and superior performance across long-context tasks without requiring input-length-specific tuning.

Copied to clipboard

Yuan Tian, Zheng Zhang, Zheng Ning, Toby Li, Jonathan K. Kummerfeld, Tianyi Zhang

Programming Languages in NLP

Challenge:	Existing approaches to generate SQL from natural language are still making many mistakes . a new interaction mechanism allows users to edit a step-by-step explanation of a query to fix errors.
Approach:	They propose a mechanism that allows users to edit a step-by-step explanation of a query to fix errors.
Outcome:	The proposed approach can achieve better performance than multiple SOTA approaches on multiple datasets and 24 participants.

Few-shot Knowledge Graph-to-Text Generation with Pretrained Language Models (2021.findings-acl)

Copied to clipboard

Junyi Li, Tianyi Tang, Wayne Xin Zhao, Zhicheng Wei, Nicholas Jing Yuan, Ji-Rong Wen

TextBox: A Unified, Modularized, and Extensible Framework for Text Generation (2021.acl-demo)

Challenge:	Existing models for KG-to-text generation are based on pretrained language models.
Approach:	They propose to automatically generate a text that describes the facts in knowledge graph (KG) they leverage the excellent capacities of pretrained language models (PLMs) in language understanding and generation.
Outcome:	The proposed model outperforms all comparison methods on fully-supervised and fewshot settings.

Copied to clipboard

Junyi Li, Tianyi Tang, Gaole He, Jinhao Jiang, Xiaoxuan Hu, Puzhao Xie, Zhipeng Chen, Zhuohao Yu, Wayne Xin Zhao, Ji-Rong Wen

Text Generation

Challenge:	TextBox is an open-source text generation framework that is modularized and extensible.
Approach:	They propose to provide a unified, modularized, and extensible text generation framework that implements 21 text generation models on 9 benchmark datasets.
Outcome:	The proposed framework implements 21 models on 9 benchmark datasets and is available under the Apache License 2.0 license.

MASTER: A Multi-Agent System with LLM Specialized MCTS (2025.naacl-long)

Copied to clipboard

Bingzheng Gan, Yufan Zhao, Tianyi Zhang, Jing Huang, Li Yusu, Shu Xian Teo, Changwang Zhang, Wei Shi

Challenge:	Large Language Models (LLMs) are increasingly being explored for problem-solving tasks . their strategic planning capability is often viewed with skepticism due to their limited planning capabilities.
Approach:	They propose a framework that coordinates agent recruitment and communication through LLM specialized MCTS.
Outcome:	The proposed framework achieves 76% accuracy on HotpotQA and 80% on WebShop . it relies on extensive sampling simulations to approximate the true reward distribution .

ElitePLM: An Empirical Study on General Language Ability Evaluation of Pretrained Language Models (2022.naacl-main)

Copied to clipboard

Junyi Li, Tianyi Tang, Zheng Gong, Lixin Yang, Zhuohao Yu, Zhipeng Chen, Jingyuan Wang, Xin Zhao, Ji-Rong Wen

ELMER: A Non-Autoregressive Pre-trained Language Model for Efficient and Effective Text Generation (2022.emnlp-main)

Challenge:	Recent years have featured a trend towards Transformer based pretrained language models (PLMs) in natural language processing systems.
Approach:	They propose to use four evaluation dimensions to evaluate ten widely-used PLMs . they find that pretrained language models are good at different ability tests .
Outcome:	The results show that pretrained language models are good at different ability tests and have excellent transferability between tasks.

Copied to clipboard

Junyi Li, Tianyi Tang, Wayne Xin Zhao, Jian-Yun Nie, Ji-Rong Wen