Papers by Kung-Hsiang Huang

21 papers
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

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

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

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

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

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

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

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

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

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

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.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations