Ratish Surendran Puduppully — accepted AI-conference papers

2026

The Illusion of Generalization: Instruction-Following, Task Bias and Contamination in Tabular Language Model Evaluation

Aditya Gorla, Ratish Surendran Puduppully

ICML 2026poster

Tabular Language Models (TLMs) have been claimed to achieve emergent generalization for tabular prediction. We conduct a systematic re-evaluation of Tabula-8B as a representative TLM, utilizing 165 datasets from the UniPredict benchmark. Our investigation reveals three findings. First, binary and ca…

Cited by 0 Source ↗Scholar ↗

2023

Multi-Document Summarization with Centroid-Based Pretraining

Ratish Surendran Puduppully, Parag Jain, Nancy Chen, Mark Steedman

ACL 2023short

In Multi-Document Summarization (MDS), the input can be modeled as a set of documents, and the output is its summary. In this paper, we focus on pretraining objectives for MDS. Specifically, we introduce a novel pretraining objective, which involves selecting the ROUGE-based centroid of each documen…

Cited by 13 Source ↗PDF ↗code ↗Scholar ↗