Papers by Zhiyuan Hu
Knowledgeable Prompt-tuning: Incorporating Knowledge into Prompt Verbalizer for Text Classification (2022.acl-long)
Copied to clipboard
| Challenge: | Recent studies suggest that pre-trained language models have gained rich knowledge during pre-training. |
| Approach: | They propose to tune pre-trained language models with task-specific prompts to improve and stabilize prompttuning. |
| Outcome: | Extensive experiments on zero and few-shot text classification tasks show that prompt-tuning improves and stabilizes prompttun-ing. |
Encoding and Controlling Global Semantics for Long-form Video Question Answering (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to find answers for long videos fail to reason over the whole sequence of video, leading to sub-optimal performance. |
| Approach: | They propose a state space layer to integrate global semantics into video . they use a gating unit to enable controllability over the flow of global semantic into visual representations. |
| Outcome: | The proposed framework is able to integrate global semantics into visual representations. |
OpenPrompt: An Open-source Framework for Prompt-learning (2022.acl-demo)
Copied to clipboard
| Challenge: | Prompt-learning is a new paradigm in natural language processing, adapting pre-trained language models to cloze-style prediction, autoregressive modeling, or sequence to sequence generation. |
| Approach: | They propose a framework for prompt-learning that integrates pre-trained language models with a unified framework. |
| Outcome: | The proposed framework is easy to use and flexible enough to integrate with other frameworks. |
COPEN: Probing Conceptual Knowledge in Pre-trained Language Models (2022.emnlp-main)
Copied to clipboard
| 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. |
KACC: A Multi-task Benchmark for Knowledge Abstraction, Concretization and Completion (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing studies focus on partial aspects of knowledge abstraction, concretization, and completion (KACC). |
| Approach: | They propose a unified knowledge graph benchmark to improve existing benchmarks . they collect new datasets that contain larger concept graphs and cross-view links . |
| Outcome: | The proposed benchmark improves existing benchmarks in terms of dataset scale, task coverage, and difficulty. |
OpenDelta: A Plug-and-play Library for Parameter-efficient Adaptation of Pre-trained Models (2023.acl-demo)
Copied to clipboard
| Challenge: | Existing implementations that modify the code of the backbone PTMs and hard-code specific delta tuning methods for each PTM have limited the practicality and flexibility of delta tuning. |
| Approach: | They propose an open-source library that provides a plug-and-play implementation of delta tuning methods for pre-trained models. |
| Outcome: | The proposed methods eliminate the need to modify the backbone PTMs’ code, making OpenDelta compatible with different, even novel PTM. |
Exploring Lottery Prompts for Pre-trained Language Models (2023.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to optimize pre-trained language models are expensive and slow to scale. |
| Approach: | They propose to search for instance-level lottery prompts and generalize them to unseen data . they validate the assumption that for every instance, there is almost always a lottery prompt that induces the correct prediction from the PLM . |
| Outcome: | The proposed method can achieve comparable results with other gradient-free and optimization-free baselines. |
Modeling User Satisfaction Dynamics in Dialogue via Hawkes Process (2023.acl-long)
Copied to clipboard
| Challenge: | Existing estimators measure performance by user satisfaction but ignore satisfaction dynamics across turns. |
| Approach: | They propose to use user satisfaction estimation to estimate performance of dialogue systems by using an estimator to simulate users. |
| Outcome: | The proposed estimator outperforms existing estimators on four benchmark dialogue datasets. |
Low-Resource Name Tagging Learned with Weakly Labeled Data (D19-1)
Copied to clipboard
| Challenge: | Existing methods for name tagging in low-resource languages or domains require extensive human efforts for training annotations. |
| Approach: | They propose a neural model for name tagging based on weakly labeled (WL) data. |
| Outcome: | The proposed model outperforms existing models in five low-resource languages and fine-grained food domains and shows that it is more efficient and efficient than existing models. |
Diagnosing Hidden Instabilities in Model Editing via Uncertainty Quantification (2026.acl-long)
Copied to clipboard
Zihan Gu, TianYi Zhang, Xinyan Zhang, Zhiyuan Wang, Han Zhang, Yuhao Wei, Jiacheng Lu, Tianyi Ma, Xingsheng Zhang, Hua Zhang, Yue Hu
| Challenge: | Existing methods to update large language models (LLMs) without expensive retraining are fragile under single-edit evaluation protocols. |
| Approach: | They propose a framework that characterizes activation-based editing as a constrained intervention on intermediate representations. |
| Outcome: | The proposed method reveals local knowledge conflicts invisible to existing benchmarks. |
Exploring the Impact of Model Scaling on Parameter-Efficient Tuning (2023.emnlp-main)
Copied to clipboard
Yusheng Su, Chi-Min Chan, Jiali Cheng, Yujia Qin, Yankai Lin, Shengding Hu, Zonghan Yang, Ning Ding, Xingzhi Sun, Guotong Xie, Zhiyuan Liu, Maosong Sun
| Challenge: | Parameter-efficient tuning (PET) methods can drive large pre-trained language models by training only minimal parameters. |
| Approach: | They propose a parameter-efficient tuning method that is compatible with a tunable module and uses a random number generator to optimize fewer table parameters. |
| Outcome: | The proposed method is compatible with a tunable module and tested on 11 NLP tasks. |
CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph Databases (2025.naacl-long)
Copied to clipboard
Xiangyan Liu, Bo Lan, Zhiyuan Hu, Yang Liu, Zhicheng Zhang, Fei Wang, Michael Qizhe Shieh, Wenmeng Zhou
| Challenge: | Large Language Models excel in stand-alone code tasks but struggle with handling entire code repositories. |
| Approach: | They propose a system that integrates LLM agents with graph database interfaces extracted from code repositories. |
| Outcome: | The proposed system integrates LLM agents with graph database interfaces extracted from code repositories. |
Utility-Oriented Visual Evidence Selection for Multimodal Retrieval-Augmented Generation (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for multimodal retrieval-augmented generation rely on semantic relevance or surface-level similarity, which are often misaligned with the actual utility of visual evidence for downstream reasoning. |
| Approach: | They propose a latent notion of evidence usefulness and propose 'surrogate-accelerated' framework that efficiently estimates evidence utility using lightweight multimodal models. |
| Outcome: | The proposed framework outperforms state-of-the-art models while achieving substantial reductions in computational cost. |
OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems (2024.acl-long)
Copied to clipboard
Chaoqun He, Renjie Luo, Yuzhuo Bai, Shengding Hu, Zhen Thai, Junhao Shen, Jinyi Hu, Xu Han, Yujie Huang, Yuxiang Zhang, Jie Liu, Lei Qi, Zhiyuan Liu, Maosong Sun
| Challenge: | Large Language Models (LLMs) and Large Multimodal Models have exceeded general human capabilities in various tasks. |
| Approach: | They present an Olympiad-level bilingual multimodal scientific benchmark featuring 8,476 problems from Olympiad level mathematics and physics competitions. |
| Outcome: | The best performing model, GPT-4V, attains an average score of 17.97% on OlympiadBench, with a mere 10.74% in physics, highlighting the benchmark rigor and the intricacy of physical reasoning. |
Prototypical Verbalizer for Prompt-based Few-shot Tuning (2022.acl-long)
Copied to clipboard
| Challenge: | Prompt-based tuning for pre-trained language models has shown its effectiveness in few-shot learning. |
| Approach: | They propose a prototypical verbalizer which learns prototype vectors as verbalizes by contrastive learning. |
| Outcome: | The proposed verbalizer outperforms existing verbalizing methods on topic classification and entity typing tasks. |
Does Memory Need Graphs? A Unified Framework and Empirical Analysis for Long-Term Dialog Memory (2026.acl-long)
Copied to clipboard
| Challenge: | Existing literature on dialog memory systems is inconsistent on their effectiveness . empirical findings on graph structures are difficult to attribute to specific design choices . |
| Approach: | They propose a framework that decomposes dialog memory systems into core components . they conduct stage-wise experiments on LongMemEval and HaluMeM, and compare implementation details . |
| Outcome: | The proposed framework compares graph-based and non-graph memory architectures on long-term dialog memory systems. |
GUICourse: From General Vision Language Model to Versatile GUI Agent (2025.acl-long)
Copied to clipboard
Wentong Chen, Junbo Cui, Jinyi Hu, Yujia Qin, Junjie Fang, Yue Zhao, Chongyi Wang, Jun Liu, Guirong Chen, Yupeng Huo, Yuan Yao, Yankai Lin, Zhiyuan Liu, Maosong Sun
| Challenge: | Graphical User Interfaces (GUIs) are a pivotal medium for human-computer interaction. |
| Approach: | They propose a series of datasets for training visual-based GUI agents using general VLMs. |
| Outcome: | The proposed GUICourse datasets show that even a small-sized GUI agent performs better on GUI tasks. |
BehaviorSFT: Behavioral Token Conditioning for Health Agents Across the Proactivity Spectrum (2025.findings-emnlp)
Copied to clipboard
Yubin Kim, Zhiyuan Hu, Hyewon Jeong, Eugene W Park, Shuyue Stella Li, Chanwoo Park, Shiyun Xiong, MingYu Lu, Hyeonhoon Lee, Xin Liu, Daniel McDuff, Cynthia Breazeal, Samir Tulebaev, Hae Won Park
| Challenge: | Large Language Models (LLMs) struggle with proactive engagement, authors say . a blind clinical evaluation confirmed that trained agents exhibit more realistic clinical behavior . |
| Approach: | They propose a training strategy using behavioral tokens to explicitly condition LLMs for dynamic behavioral selection. |
| Outcome: | The proposed training strategy boosts performance on both benchmarks. |
DecorateLM: Data Engineering through Corpus Rating, Tagging, and Editing with Language Models (2024.emnlp-main)
Copied to clipboard
Ranchi Zhao, Zhen Thai, Yifan Zhang, Shengding Hu, Jie Zhou, Yunqi Ba, Jie Cai, Zhiyuan Liu, Maosong Sun
| Challenge: | Large Language Models (LLMs) are pre-trained on vast datasets composed of billions of tokens harvested from diverse text sources. |
| Approach: | They propose a data engineering method to refine the pretraining corpus through data rating, tagging and editing. |
| Outcome: | The proposed method improves the quality of the pretraining corpus by enhancing 100 billion tokens of the training corpus. |
MAgIC: Investigation of Large Language Model Powered Multi-Agent in Cognition, Adaptability, Rationality and Collaboration (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) have advanced natural language processing, demonstrating exceptional reasoning, tool usage, and memory capabilities. |
| Approach: | They propose a competition-based benchmark framework specifically designed to assess LLMs within multi-agent environments. |
| Outcome: | The proposed framework enhances the LLMs’ abilities in navigating complex social and cognitive dimensions by over threefold between the strongest and weakest LLM models. |
Beyond the Turn-Based Game: Enabling Real-Time Conversations with Duplex Models (2024.emnlp-main)
Copied to clipboard
Xinrong Zhang, Yingfa Chen, Shengding Hu, Xu Han, Zihang Xu, Yuanwei Xu, Weilin Zhao, Maosong Sun, Zhiyuan Liu
| Challenge: | Large language models (LLMs) are increasingly permeating daily lives and require real-time interactions that mirror human conversations. |
| Approach: | They propose to use time-division-multiplexing to process queries and responses pseudo-simultaneously. |
| Outcome: | The proposed model can listen to users while generating output and adjust to provide instant feedback. |
Beyond ’Aha!’: Toward Systematic Meta-Abilities Alignment in Large Reasoning Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Prior work has shown that outcome-based reinforcement learning (RL) can incidentally elicit advanced reasoning behaviors such as self-correction, backtracking, and verification. |
| Approach: | They explicitly align large reasoning models with three meta-abilities: deduction, induction, and abduction, using automatically generated, self-verifiable tasks. |
| Outcome: | The proposed model aligns models with deduction, induction, and abduction meta-abilities using automatically generated, self-verifiable tasks. |
UltraEval: A Lightweight Platform for Flexible and Comprehensive Evaluation for LLMs (2024.acl-demos)
Copied to clipboard
Chaoqun He, Renjie Luo, Shengding Hu, Ranchi Zhao, Jie Zhou, Hanghao Wu, Jiajie Zhang, Xu Han, Zhiyuan Liu, Maosong Sun
| Challenge: | Existing evaluation platforms are complex and poorly modularized, hindering seamless incorporation into researcher’s workflows. |
| Approach: | They propose a lightweight evaluation framework characterized by lightweight, comprehensiveness, modularity, and efficiency that integrates models, data, and metrics into a unified evaluation workflow. |
| Outcome: | The proposed evaluation framework is lightweight, comprehensive, modular, and efficient. |
LongRecipe: Recipe for Efficient Long Context Generalization in Large Language Models (2025.acl-long)
Copied to clipboard
Zhiyuan Hu, Yuliang Liu, Jinman Zhao, Suyuchen Wang, WangYan WangYan, Wei Shen, Qing Gu, Anh Tuan Luu, See-Kiong Ng, Zhiwei Jiang, Bryan Hooi
| Challenge: | Large language models face significant challenges in handling long-context tasks because of their limited effective context window size during pretraining, which restricts their ability to generalize over extended sequences. |
| Approach: | They propose a training strategy for extending the context window of LLMs including impactful token analysis, position index transformation, and training optimization strategies. |
| Outcome: | Experiments on three types of LLMs show that LongRecipe can utilize long sequences while requiring only 30% of the target context window size. |
Won’t Get Fooled Again: Answering Questions with False Premises (2023.acl-long)
Copied to clipboard
| Challenge: | Pre-trained language models (PLMs) are often easily deceived by tricky questions such as “How many eyes does the sun have?” . |
| Approach: | They annotate a FalseQA dataset containing 2365 human-written FPQs and find that PLMs are capable of discriminating FPqs by fine-tuning on moderate numbers. |
| Outcome: | The proposed model can discriminate on FPQs by fine-tuning on moderate numbers of examples and generate reasonable explanations for false premise questions. |
Enhancing Chat Language Models by Scaling High-quality Instructional Conversations (2023.emnlp-main)
Copied to clipboard
| Challenge: | a recent study validates the effectiveness of chat language models by fine-tuning instruction data. |
| Approach: | They propose to use a large-scale dataset of instructional conversations to fine-tune a conversational model on instruction data. |
| Outcome: | The proposed model outperforms open-source models in key metrics including scale, average length, diversity, coherence, etc. |
RealMem: Benchmarking LLMs in Real-World Memory-Driven Interaction (2026.findings-acl)
Copied to clipboard
Haonan Bian, Zhiyuan Yao, Sen Hu, Zishan Xu, Shaolei Zhang, Yifu Guo, Ziliang Yang, Xueran Han, Huacan Wang, Ronghao Chen
| Challenge: | Existing benchmarks focus on casual conversation or task-oriented dialogue, failing to capture “long-term project-oriented” interactions where agents must track evolving goals. |
| Approach: | They propose a benchmark that simulates the dynamic evolution of memory in real-world projects. |
| Outcome: | The proposed benchmarks simulate the dynamic evolution of memory in real-world projects. |
Multi-Modal Multi-Granularity Tokenizer for Chu Bamboo Slips (2025.coling-main)
Copied to clipboard
| Challenge: | Using a multi-modal multi-granularity tokenizer, we analyze ancient Chinese scripts . a large proportion of the characters in ancient Chinese are rare or undeciphered . |
| Approach: | They propose a multi-modal multi-granularity tokenizer specifically designed for ancient Chinese scripts. |
| Outcome: | The proposed tokenizer improves on the part-of-speech tagging task on the Chu bamboo slip script. |
Syntax Encoding with Application in Authorship Attribution (D18-1)
Copied to clipboard
| Challenge: | Existing approaches to extract syntactic features from text or sentences are limited by the loss of rich structural information contained in the syntax tree. |
| Approach: | They propose to embed the syntax parse tree of sentence into a learnable distributed representation . they show that the approach improves upon the prior art and achieves new performance records . |
| Outcome: | The proposed approach improves upon the prior art and achieves new performance records on five benchmarking data sets. |
Rewarding the Rare: Uniqueness-Aware RL for Creative Problem Solving in LLMs (2026.findings-acl)
Copied to clipboard
Zhiyuan Hu, Yucheng Wang, Yufei He, Jiaying Wu, Yilun Zhao, See-Kiong Ng, Cynthia Breazeal, Anh Tuan Luu, Hae Won Park, Bryan Hooi
| Challenge: | Reinforcement learning (RL) is a paradigm for post-training large language models, but it suffers from exploration collapse . a new study finds that RL fails to reward correct solutions that exhibit rare high-level strategies . |
| Approach: | They propose a method that rewards correct solutions that exhibit rare high-level strategies by clustering rollouts according to their high- level solution strategies. |
| Outcome: | The proposed approach improves pass@k across large sampling budgets and increases area under the pass@K curve (AUC@K) without sacrificing pass@1. |
Few-Shot Charge Prediction with Discriminative Legal Attributes (C18-1)
Copied to clipboard
| Challenge: | Existing works on charge prediction perform well on high-frequency charges but are not capable of predicting few-shot charges with limited cases. |
| Approach: | They propose an attribute-attentive charge prediction model to infer attributes and charges simultaneously . they propose to use discriminative attributes as the internal mapping between fact descriptions and charges . |
| Outcome: | The proposed model outperforms baseline models on real-world datasets by more than 50% . the proposed model can predict the attributes and charges simultaneously . |
LexRel: Benchmarking Legal Relation Extraction for Chinese Civil Cases (2026.acl-long)
Copied to clipboard
Yida Cai, Ranjuexiao Hu, Huiyuan Xie, Chenyang Li, Yun Liu, Yuxiao Ye, Zhenghao Liu, Weixing Shen, Zhiyuan Liu
| Challenge: | Legal relations are an important analytical framework for dispute resolution in civil cases. |
| Approach: | They propose a comprehensive schema for legal relations in civil cases with hierarchical taxonomy and definitions of arguments. |
| Outcome: | The proposed schema shows that existing LLMs lack the ability to identify civil legal relations and performance improves on downstream tasks. |
ProSparse: Introducing and Enhancing Intrinsic Activation Sparsity within Large Language Models (2025.coling-main)
Copied to clipboard
Chenyang Song, Xu Han, Zhengyan Zhang, Shengding Hu, Xiyu Shi, Kuai Li, Chen Chen, Zhiyuan Liu, Guangli Li, Tao Yang, Maosong Sun
| Challenge: | Activation sparsity is a promising paradigm for accelerating model inference . few large language models achieve high activation spar and comparable performance . |
| Approach: | They propose a method to achieve activation sparsity and acceleration in large language models . they introduce ReLU activation and adopt progressive sparse regularization . |
| Outcome: | The proposed method achieves high activation sparsity and comparable model performance. |
LEGENT: Open Platform for Embodied Agents (2024.acl-demos)
Copied to clipboard
Zhili Cheng, Zhitong Wang, Jinyi Hu, Shengding Hu, An Liu, Yuge Tu, Pengkai Li, Lei Shi, Zhiyuan Liu, Maosong Sun
| Challenge: | Existing integrations of large language models and large multimodal models are limited . Existing platforms for developing embodied agents are limited and limited based on open-source software. |
| Approach: | They propose an open platform for developing embodied agents using LLMs and LMMs. |
| Outcome: | The proposed platform surpasses GPT-4V in embodied tasks with its model training on LEGENT data. |