Papers by Yue Gao
Ethos: Rectifying Language Models in Orthogonal Parameter Space (2024.findings-naacl)
Copied to clipboard
| Challenge: | Language models (LMs) generate toxic, biased content and reveal private training records. |
| Approach: | They propose an efficient approach that rectifies LMs to mitigate toxicity and bias . Ethos distinguishes general beneficial and undesired knowledge when reconstructing task vectors . |
| Outcome: | The proposed approach mitigates toxicity and bias in outputs and avoids privacy leakage. |
AdaTooler-V: Adaptive Tool-Use for Images and Videos (2026.findings-acl)
Copied to clipboard
Chaoyang Wang, Kaituo Feng, Dongyang Chen, Zhongyu Wang, Zhixun Li, Sicheng Gao, Meng Meng, Xu Zhou, Manyuan Zhang, Yuzhang Shang, Xiangyu Yue
| Challenge: | Existing models exhibit blind tool-use reasoning patterns, which significantly increases inference overhead and degrades model performance. |
| Approach: | They propose an MLLM that performs adaptive tool-use by determining whether a visual problem truly requires tools. |
| Outcome: | The proposed model outperforms existing methods in visual reasoning tasks. |
CityEQA: A Hierarchical LLM Agent on Embodied Question Answering Benchmark in City Space (2025.emnlp-main)
Copied to clipboard
Yong Zhao, Kai Xu, Zhengqiu Zhu, Yue Hu, Zhiheng Zheng, Yingfeng Chen, Yatai Ji, Chen Gao, Yong Li, Jincai Huang
| Challenge: | Embodied Question Answering (EQA) tasks are primarily focused on indoor environments, leaving the complexities of urban settings unexplored. |
| Approach: | They propose a task where an embodied agent answers open-vocabulary questions in dynamic city spaces. |
| Outcome: | The proposed agent achieves 60.7% of human-level answering accuracy compared to baselines . the proposed agent outperforms existing agents in open-ended city spaces . |
Learning to Use Tools via Cooperative and Interactive Agents (2024.findings-emnlp)
Copied to clipboard
Zhengliang Shi, Shen Gao, Xiuyi Chen, Yue Feng, Lingyong Yan, Haibo Shi, Dawei Yin, Pengjie Ren, Suzan Verberne, Zhaochun Ren
| Challenge: | Existing methods for large language models (LLMs) use one agent to iterate and execute tools, but they suffer from performance degradation when addressing practical tasks. |
| Approach: | They propose a tool learning framework that coordinates three specialized agents for tool selection, tool execution, and action calibration separately. |
| Outcome: | The proposed framework outperforms baseline models on three datasets with 14% higher success rate. |
HiGen: Hierarchy-Aware Sequence Generation for Hierarchical Text Classification (2024.eacl-long)
Copied to clipboard
| Challenge: | Hierarchical text classification is a complex subtask under multi-label text classification . the relevance of document sections can vary based on the hierarchy level, necessitating a dynamic document representation. |
| Approach: | They propose a text-generation-based framework that uses language models to encode dynamic text representations. |
| Outcome: | The proposed framework surpasses existing methods while handling data and mitigating class imbalance. |
Beyond Single-View Detection: A Dual-Space Reasoning Framework for Interpretable Harmful Meme Understanding (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for identifying harmful memes rely on modal alignment or black-box classifiers . BPDMoE-Hate provides visual explanations for viewpoint selection and hierarchical structuring . |
| Approach: | They propose a framework that conceptualizes harmful meme detection as a process of "viewpoint decoupling and hierarchical fusion" they propose BPDMoE-Hate, which generates adversarial binary perspectives via VLMs and incorporates an adaptive viewpoint gating to facilitate viewpoint selection. |
| Outcome: | The proposed framework surpasses existing methods in performance and provides visual explanations for viewpoint selection and hierarchical structuring. |
TaxPraBen: A Scalable Benchmark for Structured Evaluation of LLMs in Chinese Real-World Tax Practice (2026.acl-long)
Copied to clipboard
| Challenge: | Large Language Models excel in general domains but lack real-world practical capabilities. |
| Approach: | They propose a benchmark for Chinese taxation practice that combines 10 traditional application tasks with 3 pioneering real-world scenarios. |
| Outcome: | The proposed benchmark combines 10 traditional tasks with 3 pioneering real-world scenarios. |
Model Surgery: Modulating LLM’s Behavior Via Simple Parameter Editing (2025.naacl-long)
Copied to clipboard
| Challenge: | Current approaches for detoxification or preventing jailbreaking involve fine-tuning billions of parameters through gradient descent with substantial computational cost. |
| Approach: | They propose to use supervised fine-tuning and Reinforcement Learning from human feedback to modify LLMs' behavior by directly editing a small subset of parameters. |
| Outcome: | Experiments show that editing a small subset of parameters can modulate specific behaviors of LLMs, such as detoxification and resistance to jailbreak, with only inference-level computational resources. |
HiddenDetect: Detecting Jailbreak Attacks against Multimodal Large Language Models via Monitoring Hidden States (2025.acl-long)
Copied to clipboard
| Challenge: | Existing studies focus on posthoc alignment techniques, but the underlying safety mechanisms within LVLMs remain unexplored. |
| Approach: | They propose a tuning-free framework that leverages internal activations to enhance safety. |
| Outcome: | The proposed framework outperforms state-of-the-art methods in detecting jailbreak attacks against large vision-language models. |
CityCube: Benchmarking Cross-view Spatial Reasoning on Vision-Language Models in Urban Environments (2026.acl-long)
Copied to clipboard
Haotian Xu, Yue Hu, Zhengqiu Zhu, Chen Gao, Ziyou Wang, Junreng Rao, Wenhao Lu, Weishi Li, Quanjun Yin, Yong Li
| Challenge: | Existing benchmarks focus on indoor or street settings, overlooking challenges of open-ended urban spaces. |
| Approach: | They propose a benchmark to probe cross-view spatial reasoning capabilities of current VLMs in urban settings. |
| Outcome: | The citycube benchmark examines the performance of current vision-language models in urban environments. |
UrbanLLM: Autonomous Urban Activity Planning and Management with Large Language Models (2024.findings-emnlp)
Copied to clipboard
| Challenge: | UrbanLLM is a fine-tuned large language model designed to tackle diverse urban problems. |
| Approach: | They propose a fine-tuned large language model to tackle diverse urban problems . UrbanLLM decomposes urban-related queries into manageable sub-tasks . |
| Outcome: | The proposed model outperforms existing models in urban planning and management tasks. |
Beyond Single-Audio: Advancing Multi-Audio Processing in Audio Large Language Models (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing evaluations of audio large language models focus on single audio inputs, but real-world applications often require processing multiple audio streams simultaneously. |
| Approach: | They propose a multi-audio evaluation benchmark that combines 20 audio inputs from 11 audio tasks to capture audio context. |
| Outcome: | The proposed model outperforms baseline models and achieves high data efficiency without human annotations. |
FactMix: Using a Few Labeled In-domain Examples to Generalize to Cross-domain Named Entity Recognition (2022.coling-1)
Copied to clipboard
| Challenge: | Existing approaches for few-shot Named Entity Recognition (NER) are evaluated mainly under in-domain settings, but little is known about how these models perform in cross-domain NER using labeled in- domain examples. |
| Approach: | They propose to use a rationale-centric data augmentation method to improve model generalization ability by allowing model to learn from a few labeled examples in a new target domain. |
| Outcome: | The proposed method improves the performance of cross-domain NER tasks compared to the counterfactual data augmentation and prompt-tuning methods. |
Does it Make Sense? And Why? A Pilot Study for Sense Making and Explanation (P19-1)
Copied to clipboard
| Challenge: | Existing benchmarks measure common sense knowledge indirectly or without reasoning. |
| Approach: | They propose a benchmark to test whether a system can differentiate natural language statements that make sense from those that do not make sense. |
| Outcome: | The proposed benchmarks show that models trained on large corpora perform better than humans on some benchmarks. |
MCMH: Learning Multi-Chain Multi-Hop Rules for Knowledge Graph Reasoning (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing work on knowledge graphs infers a missing relationship between entities with a multi-hop rule . Empirical results show that our multi-chain multi-homing (MCMH) rules yield superior results compared to the standard single-chain approaches. |
| Approach: | They propose to use a generalized form of multi-hop rules to learn generalized rules efficiently . they propose to select a small set of relation chains as a rule and evaluate confidence . |
| Outcome: | The proposed method outperforms the existing methods and the existing frameworks. |
UrbanVideo-Bench: Benchmarking Vision-Language Models on Embodied Intelligence with Video Data in Urban Spaces (2025.acl-long)
Copied to clipboard
Baining Zhao, Jianjie Fang, Zichao Dai, Ziyou Wang, Jirong Zha, Weichen Zhang, Chen Gao, Yue Wang, Jinqiang Cui, Xinlei Chen, Yong Li
| Challenge: | Large multimodal models exhibit remarkable intelligence, yet their embodied cognitive abilities during motion in open-ended urban aerial spaces remain to be explored. |
| Approach: | They propose a benchmark to evaluate whether large multimodal models can process continuous first-person visual observations like humans. |
| Outcome: | The proposed model can process first-person visual observations like humans, enabling recall, perception, reasoning, and navigation. |
LLM-as-a-Coauthor: Can Mixed Human-Written and Machine-Generated Text Be Detected? (2024.findings-naacl)
Copied to clipboard
Qihui Zhang, Chujie Gao, Dongping Chen, Yue Huang, Yixin Huang, Zhenyang Sun, Shilin Zhang, Weiye Li, Zhengyan Fu, Yao Wan, Lichao Sun
| Challenge: | Current research focuses on purely MGT detection without adequately addressing mixed scenarios including AI-revised Human-Written Text (HWT) and human-revealed MGT. |
| Approach: | They define mixtext, a form of mixed text involving both AI and human-generated content, and then use a MixSet dataset to assess their effectiveness. |
| Outcome: | The proposed detectors struggle to identify mixtext, particularly in dealing with subtle modifications and style adaptability. |
MobileWorld: Benchmarking Autonomous Mobile Agents in Agent-User Interactive and MCP-Augmented Environments (2026.acl-long)
Copied to clipboard
Quyu Kong, Xu Zhang, Zhenyu Yang, Nolan Gao, Chen Liu, Panrong Tong, Chenglin Cai, Hanzhang Zhou, Jianan Zhang, Liangyu Chen, Zhidan Liu, Steven Hoi, Yue Wang
| Challenge: | AndroidWorld is the dominant mobile GUI agent evaluation benchmark, but its success rates are low . despite reproducible emulator environment, it lacks key application categories such as e-commerce and enterprise communication. |
| Approach: | They propose a benchmark for mobile GUI agents that reflects real-world usage through long-horizon, cross-application workflows. |
| Outcome: | The proposed framework achieves over 90% success rates, while AndroidWorld is the dominant benchmark. |
Empirical Prior for Text Autoencoders (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Variational Autoencoders (VAE) are used to train generative models with latent variables. |
| Approach: | They propose a transition from Variational Autoencoders (VAE) to text autoencodeurs (AE) which model a compact latent space and preserves the capability of the language model itself. |
| Outcome: | The proposed method generates higher quality and more diverse text than the VAE-based Transformer baselines, and is more efficient than previous approaches. |
A Survey on Open Information Extraction from Rule-based Model to Large Language Model (2024.findings-emnlp)
Copied to clipboard
Liu Pai, Wenyang Gao, Wenjie Dong, Lin Ai, Ziwei Gong, Songfang Huang, Li Zongsheng, Ehsan Hoque, Julia Hirschberg, Yue Zhang
| Challenge: | Open Information Extraction (OpenIE) is a key NLP task aimed at extracting structured information from unstructured text sources. |
| Approach: | They propose to categorize OpenIE into rule-based, neural, and pre-trained large language models and discuss each within a chronological framework. |
| Outcome: | The paper categorizes OpenIE approaches into rule-based, neural, and pre-trained large language models, discussing each within a chronological framework. |
MobiZO: Enabling Efficient LLM Fine-Tuning at the Edge via Inference Engines (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are currently pre-trained and fine-tuned on large cloud servers . fine-timing on resource-constrained edge devices presents significant memory and computational demands . |
| Approach: | They propose a resource-efficient fine-tuning framework for LLMs specifically designed for edge devices. |
| Outcome: | Experiments show that MobiZO achieves substantial runtime speedups and memory savings while improving fine-tuning accuracy. |
Cross-lingual Terminology Extraction for Translation Quality Estimation (L18-1)
Copied to clipboard
| Challenge: | Using common statistical measures for termhood and unithood, we identify terms from monolingual texts and investigate the contribution of terminology to translation quality. |
| Approach: | They propose to use common statistical measures for termhood and unithood as features to train classifiers for identifying terms in cross-domain and cross-language settings. |
| Outcome: | The proposed method has shown some reliability in automatically identifying terms in human translations, but drawbacks in handling low frequency terms and term variations shall be dealt with in the future. |
VoiceBench: Benchmarking LLM-Based Voice Assistants (2026.tacl-1)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) have enabled real-time speech interactions through LLMs. |
| Approach: | They propose a benchmark specifically designed to assess LLM-based voice assistants. |
| Outcome: | The proposed benchmark measures the performance of LLM-based voice assistants across eight tasks. |
KIEval: A Knowledge-grounded Interactive Evaluation Framework for Large Language Models (2024.acl-long)
Copied to clipboard
Zhuohao Yu, Chang Gao, Wenjin Yao, Yidong Wang, Wei Ye, Jindong Wang, Xing Xie, Yue Zhang, Shikun Zhang
| Challenge: | Existing methods to detect contaminated texts focus on quantifying contamination status instead of accurately gauging model performance. |
| Approach: | They propose a Knowledge-grounded Interactive Evaluation framework which incorporates an LLM-powered “interactor” role for the first time to accomplish a dynamic contamination-resilient evaluation. |
| Outcome: | The proposed framework is based on a question in a standard LLM benchmark and can be used to evaluate models in real-world conversations. |
FreeEval: A Modular Framework for Trustworthy and Efficient Evaluation of Large Language Models (2024.emnlp-demo)
Copied to clipboard
Zhuohao Yu, Chang Gao, Wenjin Yao, Yidong Wang, Zhengran Zeng, Wei Ye, Jindong Wang, Yue Zhang, Shikun Zhang
| Challenge: | Large language models (LLMs) have revolutionized natural language processing with impressive performance across various tasks. |
| Approach: | They propose a framework for automated evaluations of large language models . they open-source their code at https://github.com/WisdomShell/FreeEval . |
| Outcome: | The framework is open-source and can be used to develop and validate new evaluation methods. |
Multimodal Machine Translation with Text-Image In-depth Questioning (2025.findings-acl)
Copied to clipboard
| Challenge: | Multimodal machine translation (MMT) models focus on intermodal interactions, but focus on simple interactions between nouns and entities in image, overlooking global semantic alignment. |
| Approach: | They propose a Text-Image In-depth Questioning method to deepen interactions and optimize translations by utilizing visual data to capture global semantic alignment. |
| Outcome: | The proposed method achieves state-of-the-art results on five translation directions of Multi30K and AmbigCaps, with +2.35 BLEU on the challenging MSCOCO benchmark. |