Papers by Haoyi Qiu
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. |
Gender Biases in Automatic Evaluation Metrics for Image Captioning (2023.emnlp-main)
Copied to clipboard
| Challenge: | Pretrained evaluation metrics can perpetuate and amplify biases, causing inability to differentiate between biased and unbiased generations. |
| Approach: | They conduct a systematic study of gender biases in image captioning tasks . they show that pretrained models perpetuate and amplify biase . |
| Outcome: | The proposed model-based evaluation metrics have shown good correlations with human judgments in language generation tasks. |
VALOR-EVAL: Holistic Coverage and Faithfulness Evaluation of Large Vision-Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing evaluation methods focus on object hallucinations, focusing on object outputs . current evaluation methods struggle to address subtle semantic distinctions between outputs and reference data . |
| Approach: | They propose a multi-dimensional benchmark covering objects, attributes, and relations . they propose metric that generalizes CHAIR metric and incorporates faithfulness and coverage . |
| Outcome: | The proposed evaluation framework is more comprehensive and better correlated with humans than existing evaluation methods. |
Attribution-Based Analysis and Optimization of Modular Agentic Workflows (2026.findings-acl)
Copied to clipboard
Yingxuan Yang, Bo Huang, Siyuan Qi, Chao Feng, Haoyi Hu, Yuxuan Zhu, Jinbo Hu, Haoran Zhao, Ziyi He, Xiao Liu, ZongYu Wang, Muning Wen, Lin Qiu, Xuezhi Cao, Xunliang Cai, Yong Yu, Weinan Zhang
| Challenge: | Large Language Models (LLMs) have driven the rise of agentic workflows . yet, how can we attribute performance gains to individual upgrades and their interactions? |
| Approach: | They propose a game-theoretic framework that models component upgrades as players and evaluates component coalitions to compute Shapley values. |
| Outcome: | The proposed framework provides interaction-aware attribution and recommendation for model allocation under a fixed workflow structure. |
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. |
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. |