10 citations · 31 across the 24 of their papers we have counts for
21 papers · 1 filter
Why Generate a Click? Plug-in Decision Heads for Web Agents
Chengguang Gan, Yunhao Liang, Hanjun Wei +3
Web agents built on vision language models decide every action by generating text such as click(12), although most of that text encodes a choice among a few action types and a few…
Auditing Web Agent Evaluation on WebArena-Lite: Human Review of Outcomes and Trajectories
Chengguang Gan, Zimeng He, Yoshihiro Tsujii +3
Web agents are an important application of large language models, yet their evaluation often depends on rule based or language model evaluators that inspect only the final outcome.…
Certified Selective Automation of LLM Agent Evaluation
Chengguang Gan, Yunhao Liang, Qinghao Zhang +1
Evaluating LLM agents still ends with a human reading trajectories, because automatic judges carry no guarantee on how often they are wrong. We ask the operational question: what f…
Guides That Cause Actions: An Offline Study of Guide-Action Mutual Reinforcement in Multimodal Web Agents
Chengguang Gan, Yunhao Liang, QingHao Zhang +1
Web agents are usually evaluated in live environments, where environment state and judge models drift between runs, so the same checkpoint rarely reproduces the same score, making…
How Output Format Confounds Data Quality and Capability in Instruction Tuning
Chengguang Gan, Hanjun Wei, Yunhao Liang +3
Instruction-tuning data are judged by quality metrics, and tuned models are judged by benchmarks, but both judgments pass through an output interface: the surface format in which a…
Joint Training Is Not Enough: Conditioned Cross-Granularity Training for Multimodal Document Understanding
Chengguang Gan, Yunhao Liang, Hanjun Wei +2
The Mutual Reinforcement Effect (MRE) asks whether a fine, span-level and a coarse, document-level task help each other when one model handles both. We test it in multimodal docume…
GuideWeb: A Benchmark for Automatic In-App Guide Generation on Real-World Web UIs
Chengguang Gan, Yoshihiro Tsujii, Yunhao Liang +3
Digital Adoption Platform (DAP) provide web-based overlays that deliver operation guidance and contextual hints to help users navigate complex websites. Although modern DAP tools e…
M-MRE: Extending the Mutual Reinforcement Effect to Multimodal Information Extraction
Chengguang Gan, Zhixi Cai, Yanbin Wei +3
Mutual Reinforcement Effect (MRE) is an emerging subfield at the intersection of information extraction and model interpretability. MRE aims to leverage the mutual understanding be…
Empirical Study of Mutual Reinforcement Effect and Application in Few-shot Text Classification Tasks via Prompt
Chengguang Gan, Tatsunori Mori
The Mutual Reinforcement Effect (MRE) investigates the synergistic relationship between word-level and text-level classifications in text classification tasks. It posits that the p…
A Multilingual Dataset and Empirical Validation for the Mutual Reinforcement Effect in Information Extraction
Chengguang Gan, Sunbowen Lee, Qingyu Yin +9
The Mutual Reinforcement Effect (MRE) describes a phenomenon in information extraction where word-level and sentence-level tasks can mutually improve each other when jointly modele…
II-Bench: An Image Implication Understanding Benchmark for Multimodal Large Language Models
Ziqiang Liu, Feiteng Fang, Xi Feng +23
The rapid advancements in the development of multimodal large language models (MLLMs) have consistently led to new breakthroughs on various benchmarks. In response, numerous challe…
Demonstrating Mutual Reinforcement Effect through Information Flow
Chengguang Gan, Xuzheng He, Qinghao Zhang +1
The Mutual Reinforcement Effect (MRE) investigates the synergistic relationship between word-level and text-level classifications in text classification tasks. It posits that the p…
Application of LLM Agents in Recruitment: A Novel Framework for Resume Screening
Chengguang Gan, Qinghao Zhang, Tatsunori Mori
The automation of resume screening is a crucial aspect of the recruitment process in organizations. Automated resume screening systems often encompass a range of natural language p…
Think from Words(TFW): Initiating Human-Like Cognition in Large Language Models Through Think from Words for Japanese Text-level Classification
Chengguang Gan, Qinghao Zhang, Tatsunori Mori
The proliferation of Large Language Models (LLMs) has spurred extensive research into LLM-related Prompt investigations, such as Instruction Learning (IL), In-context Learning (ICL…
GIELLM: Japanese General Information Extraction Large Language Model Utilizing Mutual Reinforcement Effect
Chengguang Gan, Qinghao Zhang, Tatsunori Mori
Information Extraction (IE) stands as a cornerstone in natural language processing, traditionally segmented into distinct sub-tasks. The advent of Large Language Models (LLMs) hera…
USA: Universal Sentiment Analysis Model & Construction of Japanese Sentiment Text Classification and Part of Speech Dataset
Chengguang Gan, Qinghao Zhang, Tatsunori Mori
Sentiment analysis is a pivotal task in the domain of natural language processing. It encompasses both text-level sentiment polarity classification and word-level Part of Speech(PO…
Mutual Reinforcement Effects in Japanese Sentence Classification and Named Entity Recognition Tasks
Chengguang Gan, Qinghao Zhang, Tatsunori Mori
Information extraction(IE) is a crucial subfield within natural language processing. However, for the traditionally segmented approach to sentence classification and Named Entity R…
Sentence-to-Label Generation Framework for Multi-task Learning of Japanese Sentence Classification and Named Entity Recognition
Chengguang Gan, Qinghao Zhang, Tatsunori Mori
Information extraction(IE) is a crucial subfield within natural language processing. In this study, we introduce a Sentence Classification and Named Entity Recognition Multi-task (…
Sensitivity and Robustness of Large Language Models to Prompt Template in Japanese Text Classification Tasks
Chengguang Gan, Tatsunori Mori
Prompt engineering relevance research has seen a notable surge in recent years, primarily driven by advancements in pre-trained language models and large language models. However,…
A Few-shot Approach to Resume Information Extraction via Prompts
Chengguang Gan, Tatsunori Mori
Prompt learning's fine-tune performance on text classification tasks has attracted the NLP community. This paper applies it to resume information extraction, improving existing met…
Construction of English Resume Corpus and Test with Pre-trained Language Models
Chengguang Gan, Tatsunori Mori
Information extraction(IE) has always been one of the essential tasks of NLP. Moreover, one of the most critical application scenarios of information extraction is the information…