Papers by Jiaru Zou
PAPERMIND: Benchmarking Agentic Reasoning and Critique over Scientific Papers in Multimodal LLMs (2026.findings-acl)
Copied to clipboard
Yanjun Zhao, Tianxin Wei, Jiaru Zou, Xuying Ning, Yuanchen Bei, Lingjie Chen, Simmi Rana, Wendy H. Yang, Hanghang Tong, Jingrui He
| Challenge: | Existing benchmarks assess integrated and agent-oriented scientific reasoning in isolation . Existing systems assess integrated reasoning in isolated tasks . |
| Approach: | They propose a benchmark to evaluate integrated and agent-oriented scientific reasoning over research papers. |
| Outcome: | The proposed benchmark evaluates integrated and agent-oriented scientific reasoning over scientific papers. |
Not All Voices Are Rewarded Equally: Probing and Repairing Reward Models across Human Diversity (2025.findings-emnlp)
Copied to clipboard
Zihao Li, Feihao Fang, Xitong Zhang, Jiaru Zou, Zhining Liu, Wei Xiong, Ziwei Wu, Baoyu Jing, Jingrui He
| Challenge: | Using real-world datasets, we conduct the most comprehensive study to date, auditing various state-of-the-art reward models across nine sensitive attributes, including age, gender, ethnicity, etc. |
| Approach: | They propose a method to mitigate group disparities in reward modeling by using real-world data. |
| Outcome: | The proposed method is based on a population-based dataset with nine demographic attributes, including gender, ethnicity, age, gender, and ethnicity. |
LLM-Forest: Ensemble Learning of LLMs with Graph-Augmented Prompts for Data Imputation (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing frameworks for missing data imputation are lacking in a finetuning-free process and mitigating biases and uncertainty in LLM outputs. |
| Approach: | They propose a framework for imputation of large language models with a forest of few-shot learning LLM "trees" they use bipartite information graphs to identify relevant neighboring entries with feature and value granularity. |
| Outcome: | The proposed framework is based on a concept of bipartite information graphs to identify high-quality relevant neighboring entries with both feature and value granularity. |
CoCoST: Automatic Complex Code Generation with Online Searching and Correctness Testing (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to improve code generation from natural language descriptions are difficult due to complex structure, subtle bugs, and lack of supplementary contents. |
| Approach: | They propose a framework that enhances complex code generation by online searching for more information with planned queries and correctness testing for code refinement. |
| Outcome: | The proposed framework improves the quality of complex code generation on the DS-1000 and ClassEval datasets. |
PromptIntern: Saving Inference Costs by Internalizing Recurrent Prompt during Large Language Model Fine-tuning (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Recent advances in fine-tuning large language models have greatly enhanced their usage in domain-specific tasks. |
| Approach: | They propose a method which internalizes prompt knowledge during model fine-tuning to achieve efficient inference and save costs. |
| Outcome: | The proposed approach reduces input tokens by 90%, accelerates inference by 4.2 times, and reduces monetary inference costs by 88.3%. |
RAG over Tables: Hierarchical Memory Index, Multi-Stage Retrieval, and Benchmarking (2026.findings-acl)
Copied to clipboard
| Challenge: | Retrieval-Augmented Generation (RAG) integrates knowledge from tables with an external knowledge base to improve the answer relevance and accuracy. |
| Approach: | They propose a table-corpora-aware RAG framework called T-RAG to integrate external knowledge into Large Language Models (LLMs) they then develop a multi-table question answering benchmark called MultiTableQA which spans 3 different task types, 57,193 tables, and 23,758 questions in total. |
| Outcome: | The proposed framework achieves state-of-the-art accuracy, recall, and runtime performance, with improvements of up to 9.4%. |
TAP4LLM: Table Provider on Sampling, Augmenting, and Packing Semi-structured Data for Large Language Model Reasoning (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing solutions for table reasoning tasks are mainly tested on small tables and face scalability issues and struggle with complex queries due to incomplete or dispersed data across different table sections. |
| Approach: | They propose a table reasoning pre-processor suite that can be used to leverage large language models (LLMs) in table-based tasks. |
| Outcome: | The proposed method improves LLMs’ reasoning capabilities in various tabular tasks and enhances interaction between LLM and tabular data by employing effective pre-processing. |
STEM-POM: Evaluating Language Models Math-Symbol Reasoning in Document Parsing (2025.findings-acl)
Copied to clipboard
| Challenge: | Advances in large language models have spurred research into enhancing their reasoning capabilities, particularly in math-rich STEM documents. |
| Approach: | They propose a benchmark dataset to evaluate LLMs’ reasoning abilities on math symbols within contextual scientific text. |
| Outcome: | The proposed dataset demonstrates that state-of-the-art LLMs achieve an average accuracy of 20-60% under in-context learning and 50-60% with fine-tuning, highlighting a substantial gap in their ability to classify mathematical symbols. |
Zero-Shot Open-Schema Entity Structure Discovery (2026.eacl-long)
Copied to clipboard
Xueqiang Xu, Jinfeng Xiao, James Barry, Mohab Elkaref, Jiaru Zou, Pengcheng Jiang, Yunyi Zhang, Maxwell J Giammona, Geeth De Mel, Jiawei Han
| Challenge: | Existing methods based on large language models (LLMs) rely heavily on predefined entity attribute schemas or annotated datasets, often leading to incomplete extraction results. |
| Approach: | They propose a novel approach to entity structure extraction that does not require any schema or annotated datasets. |
| Outcome: | Experiments show that ZOES improves LLMs’ ability to extract more complete entity structures across three different domains, showcasing both the effectiveness and generalizability of the method. |