activity
20242026
collaborators

7 papers

cs.CL2026

SOMA-SQL: Resolving Multi-Source Ambiguity in NL-to-SQL via Synthetic Log and Execution Probing

Sai Ashish Somayajula, Marianne Menglin Liu, Chuan Lei +9

Natural language interfaces to databases aim to translate user questions into executable SQL, yet remain brittle in real-world settings where questions are underspecified and schem…

cs.LG2025

DreamPRM: Domain-Reweighted Process Reward Model for Multimodal Reasoning

Qi Cao, Ruiyi Wang, Ruiyi Zhang +2

Reasoning has substantially improved the performance of large language models (LLMs) on complicated tasks. Central to the current reasoning studies, Process Reward Models (PRMs) of…

cs.CL2025

OraPlan-SQL: A Planning-Centric Framework for Complex Bilingual NL2SQL Reasoning

Marianne Menglin Liu, Sai Ashish Somayajula, Syed Fahad Allam Shah +2

We present OraPlan-SQL, our system for the Archer NL2SQL Evaluation Challenge 2025, a bilingual benchmark requiring complex reasoning such as arithmetic, commonsense, and hypotheti…

cs.CL2025

Can Prompts Rewind Time for LLMs? Evaluating the Effectiveness of Prompted Knowledge Cutoffs

Xin Gao, Ruiyi Zhang, Daniel Du +3

Large Language Models (LLMs) are widely used for temporal prediction, but their reliance on pretraining data raises contamination concerns, as accurate predictions on pre-cutoff te…

cs.CL2025

Improving the Language Understanding Capabilities of Large Language Models Using Reinforcement Learning

Bokai Hu, Sai Ashish Somayajula, Xin Pan +1

Instruction-fine-tuned large language models (LLMs) under 14B parameters continue to underperform on natural language understanding (NLU) tasks, often trailing smaller models like…

cs.CV2025

Downstream Task Guided Masking Learning in Masked Autoencoders Using Multi-Level Optimization

Han Guo, Ramtin Hosseini, Ruiyi Zhang +4

Masked Autoencoder (MAE) is a notable method for self-supervised pretraining in visual representation learning. It operates by randomly masking image patches and reconstructing the…