5 papers
Self-Improving Tabular Language Models via Iterative Reward-Guided Post-Training
Yunbo Long, Tejumade Afonja, Guangya Hao +2
Tabular language models can generate synthetic tables by modeling rows as token sequences, but they are typically trained once with supervised fine-tuning and then used as static s…
Automated Detection of Abnormalities in Zebrafish Development
Sarath Sivaprasad, Hui-Po Wang, Anna-Lisa Jäckel +4
Zebrafish embryos are a valuable model for drug discovery due to their optical transparency and genetic similarity to humans. However, current evaluations rely on manual inspection…
Accept or Deny? Evaluating LLM Fairness and Performance in Loan Approval across Table-to-Text Serialization Approaches
Israel Abebe Azime, Deborah D. Kanubala, Tejumade Afonja +4
Large Language Models (LLMs) are increasingly employed in high-stakes decision-making tasks, such as loan approvals. While their applications expand across domains, LLMs struggle t…
DP-2Stage: Adapting Language Models as Differentially Private Tabular Data Generators
Tejumade Afonja, Hui-Po Wang, Raouf Kerkouche +1
Generating tabular data under differential privacy (DP) protection ensures theoretical privacy guarantees but poses challenges for training machine learning models, primarily due t…
Language Models as Zero-shot Lossless Gradient Compressors: Towards General Neural Parameter Prior Models
Hui-Po Wang, Mario Fritz
Despite the widespread use of statistical prior models in various fields, such models for neural network gradients have long been overlooked. The inherent challenge stems from thei…