Papers by Kung-Hsiang Huang
Why Vision Language Models Struggle with Visual Arithmetic? Towards Enhanced Chart and Geometry Understanding (2025.findings-acl)
Copied to clipboard
| Challenge: | Vision Language Models struggle with visual arithmetic, seemingly simple tasks like object counting or length comparison, which are essential for relevant complex tasks like chart understanding and geometric reasoning. |
| Approach: | They propose a novel post-training strategy inspired by Piaget’s theory of cognitive development that trains VLMs to recognize invariant properties under visual transformations. |
| Outcome: | The proposed approach outperforms supervised fine-tuning methods while requiring 60% less training data. |
The Battlefront of Combating Misinformation and Coping with Media Bias (2022.aacl-tutorials)
Copied to clipboard
| Challenge: | a growing number of misinformation and misinformation is affecting our daily lives . a tutorial aims to address the challenges of detecting fake news and media bias . |
| Approach: | They provide an overview of the frontier in fighting misinformation . they propose to develop a robust fake news detection system to combat misinformation. |
| Outcome: | This tutorial examines the frontiers of fake news detection and media bias detection . it focuses on how to fact-check information pieces and uncover bias and agenda of news sources . |
Document-level Entity-based Extraction as Template Generation (2021.emnlp-main)
Copied to clipboard
| Challenge: | Document-level entity-based extraction (EE) tasks extract entity-centric information from unstructured text across multiple sentences. |
| Approach: | They propose a generative framework for two document-level EE tasks: role-filler entity extraction (RE) and relation extraction ( RE). |
| Outcome: | The proposed framework captures cross-entity dependencies and avoids exponential computation complexity of identifying N-ary relations. |
Don’t Stop Early: Scalable Enterprise Deep Research with Controlled Information Flow and Evidence-Aware Termination (2026.acl-industry)
Copied to clipboard
Prafulla Kumar Choubey, Kung-Hsiang Huang, Pranav Narayanan Venkit, Jiaxin Zhang, Vaibhav Vats, Yu Li, Xiangyu Peng, Chien-Sheng Wu
| Challenge: | Enterprise deep research systems fail to produce decision-ready reports due to uneven information coverage, context explosion, and premature stopping. |
| Approach: | They propose a scalable Enterprise Deep Research (EDR) architecture that decomposes requests into coverage-driven objectives via outline generation with reflection and localizes context with dependency-guided execution and explicit information sharing. |
| Outcome: | The proposed system achieves the strongest overall performance compared with competitive deep-research baselines on internal sales enablement tasks and the public DeepResearch Bench benchmark. |
ManiTweet: A New Benchmark for Identifying Manipulation of News on Social Media (2025.coling-main)
Copied to clipboard
| Challenge: | Existing studies have focused on the identification of social media posts that contain misrepresentations of information within associated news articles. |
| Approach: | They propose a data collection schema and curated a dataset called ManiTweet, consisting of 3.6K pairs of tweets and corresponding articles. |
| Outcome: | The proposed model outperforms large language models on the ManiTweet dataset and reveals intriguing connections between manipulation and the domain and factuality of news articles. |
Biomedical Event Extraction with Hierarchical Knowledge Graphs (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Biomedical event extraction is critical in understanding biomolecular interactions described in scientific corpus. |
| Approach: | They propose to integrate domain knowledge from Unified Medical Language System (UMLS) to a pre-trained language model using Graph Edge-conditioned Attention Networks and hierarchical graph representation. |
| Outcome: | The proposed approach achieves 1.41% F1 and 3.19% F1 improvements on the BioNLP 2011 GENIA Event Extraction task. |
M2-TabFact: Multi-Document Multi-Modal Fact Verification with Visual and Textual Representations of Tabular Data (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing fact-checking systems that can reason over structured data are inefficient compared to humans. |
| Approach: | They propose a multi-modal table-based fact verification task that requires reasoning over visual and textual representations of structured data. |
| Outcome: | The proposed model can reason over visual and textual representations of structured data. |
Cross-document Misinformation Detection based on Event Graph Reasoning (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing methods for misinformation detection are limited to judging each document in isolation. |
| Approach: | They propose a task of cross-document misinformation detection that detects fake news from a cluster of topically related news documents. |
| Outcome: | The proposed method outperforms existing methods by up to 7 F1 points on this task. |
Evaluating Cultural and Social Awareness of LLM Web Agents (2025.findings-naacl)
Copied to clipboard
Haoyi Qiu, Alexander Fabbri, Divyansh Agarwal, Kung-Hsiang Huang, Sarah Tan, Nanyun Peng, Chien-Sheng Wu
| Challenge: | Existing benchmarks often overlook cultural and social awareness . current evaluations focus on task completion, often ignoring the diverse cultural and socio-cultural backgrounds. |
| Approach: | They propose a benchmark to assess LLM agents’ sensitivity to cultural and social norms across two web-based tasks: online shopping and social discussion forums. |
| Outcome: | The proposed framework evaluates LLM agents’ ability to detect and appropriately respond to norm-violating user queries and observations across two web-based tasks. |
EventPlus: A Temporal Event Understanding Pipeline (2021.naacl-demos)
Copied to clipboard
Mingyu Derek Ma, Jiao Sun, Mu Yang, Kung-Hsiang Huang, Nuan Wen, Shikhar Singh, Rujun Han, Nanyun Peng
| Challenge: | Event information is a type of common sense knowledge that helps people understand how stories evolve and provides predictive hints for future events. |
| Approach: | They propose a temporal event understanding pipeline that integrates state-of-the-art components. |
| Outcome: | The proposed pipeline can be easily adapted to other domains, including biomedical domains. |
GTA: Generating Long-horizon Tasks for Web Agents at Scale (2026.acl-long)
Copied to clipboard
Tenghao Huang, Kung-Hsiang Huang, Prafulla Kumar Choubey, Yilun Zhou, Muhao Chen, Jonathan May, Chien-Sheng Wu
| Challenge: | Existing benchmarks provide only coarse start–goal annotations without intermediate trajectories . Existing frameworks provide no supervision over the agent's latent decision process . |
| Approach: | They propose a framework that integrates crawling, retrieval-based seeding, in-context generation and automated quality control to produce realistic tasks paired with executable trajectories. |
| Outcome: | The proposed framework decouples crawling from generation for greater efficiency and ensures dense supervision through deterministic replays and systematic validation. |
LAM SIMULATOR: Advancing Data Generation for Large Action Model Training via Online Exploration and Trajectory Feedback (2025.findings-acl)
Copied to clipboard
Thai Quoc Hoang, Kung-Hsiang Huang, Shirley Kokane, Jianguo Zhang, Zuxin Liu, Ming Zhu, Jake Grigsby, Tian Lan, Michael S Ryoo, Chien-Sheng Wu, Shelby Heinecke, Huan Wang, Silvio Savarese, Caiming Xiong, Juan Carlos Niebles
| Challenge: | Large Action Models (LAMs) face challenges due to the need for high-quality training data, especially for multi-steps tasks that involve planning, executing tool calls, and responding to feedback. |
| Approach: | They propose a framework for online exploration of agentic tasks with high-quality feedback . they use a dynamic task query generator and an extensive collection of tools to create a high-level feedback environment for LLM Agents. |
| Outcome: | The proposed framework achieves 49.3% performance improvement over baselines on toolbench and CRMArena. |
Benchmarking Deep Search over Heterogeneous Enterprise Data (2025.emnlp-industry)
Copied to clipboard
Prafulla Kumar Choubey, Xiangyu Peng, Shilpa Bhagavath, Kung-Hsiang Huang, Caiming Xiong, Chien-Sheng Wu
| Challenge: | Existing methods struggle to conduct deep searches and retrieve all necessary evidence. |
| Approach: | They propose a benchmark for evaluating deep search, a retrieval-augmented generation that requires source-aware, multi-hop reasoning over diverse, sparsed, but related sources. |
| Outcome: | The proposed benchmarks show that even the best-performing agentic RAG methods achieve an average performance score of 32.96 on the benchmark. |
Embrace Divergence for Richer Insights: A Multi-document Summarization Benchmark and a Case Study on Summarizing Diverse Information from News Articles (2024.naacl-long)
Copied to clipboard
Kung-Hsiang Huang, Philippe Laban, Alexander Fabbri, Prafulla Kumar Choubey, Shafiq Joty, Caiming Xiong, Chien-Sheng Wu
| Challenge: | Existing studies on multi-document summarization focus on collating information that all sources agree upon, but the task of summarizing diverse information remains underexplored. |
| Approach: | They propose a task of summarizing diverse information encountered in multiple news articles encompassing the same event using a dataset curated by a large language model. |
| Outcome: | The proposed task aims to summarize diverse information in multiple news articles encompassing the same event . the proposed task is difficult due to its limited coverage and verbosity biases . |
CONCRETE: Improving Cross-lingual Fact-checking with Cross-lingual Retrieval (2022.coling-1)
Copied to clipboard
| Challenge: | Existing fact-checking approaches focus on claims made in English due to data scarcity issue in other languages. |
| Approach: | They propose a fact-checking framework augmented with cross-lingual retrieval that aggregates evidence retrieved from multiple languages through a cross-linguistic retriever. |
| Outcome: | The proposed framework achieves 2.23% absolute F1 improvement over previous systems on a X-Fact dataset. |
AMRFact: Enhancing Summarization Factuality Evaluation with AMR-Driven Negative Samples Generation (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing methods for evaluating factual consistency of abstractive summarization lack coherence or error-type coverage. |
| Approach: | They propose a framework that generates perturbed summaries using Abstract Meaning Representations (AMRs) they use a selection module NegFilter to ensure the quality of the generated negative examples . |
| Outcome: | The proposed framework outperforms existing systems on the AggreFact-SOTA benchmark and provides high error-type coverage. |
SWING: Balancing Coverage and Faithfulness for Dialogue Summarization (2023.findings-eacl)
Copied to clipboard
Kung-Hsiang Huang, Siffi Singh, Xiaofei Ma, Wei Xiao, Feng Nan, Nicholas Dingwall, William Yang Wang, Kathleen McKeown
| Challenge: | Existing approaches to dialogue summarization rely on features of conversation data. |
| Approach: | They propose to use natural language inference models to improve coverage and faithfulness . they use fine-grained training signals to encourage model to generate missing content . |
| Outcome: | The proposed model achieves higher faithfulness and coverage while maintaining conciseness compared to prior methods. |
CRMArena: Understanding the Capacity of LLM Agents to Perform Professional CRM Tasks in Realistic Environments (2025.naacl-long)
Copied to clipboard
Kung-Hsiang Huang, Akshara Prabhakar, Sidharth Dhawan, Yixin Mao, Huan Wang, Silvio Savarese, Caiming Xiong, Philippe Laban, Chien-Sheng Wu
| Challenge: | Existing benchmarks for evaluating CRM agents on work-related tasks are limited due to data privacy concerns. |
| Approach: | They propose a benchmark to evaluate AI agents on real-world CRM tasks . they use 16 commonly used industrial objects with high interconnectivity to simulate real data distributions. |
| Outcome: | The new benchmark evaluates AI agents on real-world customer service tasks . it includes 16 commonly used industrial objects with high interconnectivity . the results highlight the need for enhanced agent capabilities in function-calling and rule-following . |
Zero-shot Faithful Factual Error Correction (2023.acl-long)
Copied to clipboard
| Challenge: | Using machines to correct factual errors is in high demand and requires a significant amount of human effort. |
| Approach: | They propose a zero-shot framework that asks questions about input claims and seeks correct answers from the given evidence to correct factual errors faithfully. |
| Outcome: | The proposed framework outperforms fully-supervised methods on the FEVER and SciFact datasets and is more faithful. |
Do LVLMs Understand Charts? Analyzing and Correcting Factual Errors in Chart Captioning (2024.findings-acl)
Copied to clipboard
Kung-Hsiang Huang, Mingyang Zhou, Hou Pong Chan, Yi Fung, Zhenhailong Wang, Lingyu Zhang, Shih-Fu Chang, Heng Ji
| Challenge: | LVLMs are known for producing text that is factually inconsistent with visual input . factuality of generated captions for structured visuals has not been studied as much . |
| Approach: | They propose a typology of factual errors in captions generated by large vision-language models . they propose CHOCOLATE, a visual entailment model that outperforms current models based on this analysis . |
| Outcome: | The proposed model outperforms current models in evaluating caption factuality. |
Faking Fake News for Real Fake News Detection: Propaganda-Loaded Training Data Generation (2023.acl-long)
Copied to clipboard
| Challenge: | despite advances in detecting fake news, there is a sizable gap between machine-generated and human-authored fake news . a nave solution is to collect human-written news articles that contain inaccurate information by crawling untrustworthy news media. |
| Approach: | They propose a framework for generating training examples informed by the styles and strategies of human-authored propaganda. |
| Outcome: | The proposed framework improves detection of human-written disinformation by 3.62–7.69% on two public datasets. |