Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
Language‑Bias‑Resilient Visual Question Answering via Adaptive Multi‑Margin Collaborative Debiasing
Authors: Huanjia Zhu, Shuyuan Zheng, Yishu Liu, Sudong Cai, Bingzhi Chen
NeurIPS 2025 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments across multiple challenging VQA benchmarks confirm the consistent superiority of our proposed MMCD over state-of-the-art baselines in combating language bias. |
| Researcher Affiliation | Academia | Huanjia Zhu Beijing Institute of Technology, Zhuhai EMAIL Shuyuan Zheng The University of Osaka EMAIL Yishu Liu Harbin Institute of Technology, Shenzhen EMAIL Sudong Cai Beijing Institute of Technology, Zhuhai EMAIL Bingzhi Chen Beijing Institute of Technology, Zhuhai EMAIL |
| Pseudocode | No | The paper describes the methodology using mathematical equations and narrative text but does not include any clearly labeled pseudocode or algorithm blocks. |
| Open Source Code | No | Justification: The code will be released once the paper is accepted. |
| Open Datasets | Yes | We select various OOD benchmarks to assess the robustness of models against real-world biases, such as VQA-CP v2, VQA-CP v1 [1]. All experiments adopt the standard evaluation metric [3]. |
| Dataset Splits | No | Further details on the experimental setup and implementation can be found in the supplementary materials. |
| Hardware Specification | No | We provided a description of the platform and hardware used for the experiments. |
| Software Dependencies | No | Further details on the experimental setup and implementation can be found in the supplementary materials. |
| Experiment Setup | No | Further details on the experimental setup and implementation can be found in the supplementary materials. |