Avi Sil

Senior Director, Applied Science, AI and Applied Science, Oracle

Joined

July 2019

Names

Avi Sil (Preferred)

Avirup Sil

Emails

****@us.ibm.com (Confirmed)

****@gmail.com (Confirmed)

****@oracle.com (Confirmed)

Personal Links

Homepage

DBLP

Career & Education History

Senior Director, Applied Science

AI and Applied Science, Oracle (oracle.com)

2025 – Present

Principal Researcher

AI and Automation, International Business Machines (ibm.com)

2021 – 2025

Manager

International Business Machines (ibm.com)

2014 – 2025

Advisors, Relations & Conflicts

No relations added

Expertise

Agentic Workflows

Present

LLM reasoning

Present

Embedding models

Autoregressive LLMs

Present

Publications

CLARITY: A Framework and Benchmark for Conversational Language Ambiguity and Unanswerability in Interactive NL2SQL Systems
Tabinda Sarwar, Farhad Moghimifar, Cong Duy Vu Hoang, Xiaoxiao Ma, Shawn Chang Xu, Fahimeh Saleh, Poorya Zaremoodi, Avirup Sil, Katrin Kirchhoff
- ACL 2026 Industry Track Poster
- Readers: Everyone
Let’s Try Again: Eliciting Multi-Turn Reasoning in Language Models via Simplistic Feedback
Licheng Liu, Zihan Wang, Linjie Li, Chenwei Xu, Yiping Lu, Han Liu, Avirup Sil, Manling Li
- LAW
- Readers: Everyone
FINE-GRAINED ENERGY PREDICTION FOR PARALLELIZED LLM INFERENCE WITH PIE-P
Anurag Dutt, Young Won Choi, Avirup Sil, Anshul Gandhi, Aruna Balasubramanian, Niranjan Balasubramanian
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Unary Feedback as Observation: Incentivizing Self-Reflection in Large Language Models via Multi-Turn RL
Licheng Liu, Zihan Wang, Linjie Li, Chenwei Xu, Yiping Lu, Han Liu, Avirup Sil, Manling Li
- Submitted to ICLR 2026
- Readers: Everyone
Let’s Try Again: Eliciting Multi-Turn Reasoning in Language Models via Simplistic Feedback
Licheng Liu, Zihan Wang, Linjie Li, Chenwei Xu, Yiping Lu, Han Liu, Avirup Sil, Manling Li
- MTI-LLM @ NeurIPS 2025 Poster
- Readers: Everyone
Let’s Try Again: Eliciting Multi-Turn Reasoning in Language Models via Simplistic Feedback
Licheng Liu, Zihan Wang, Linjie Li, Chenwei Xu, Yiping Lu, Han Liu, Avirup Sil, Manling Li
- AI4Math@ICML25 Poster
- Readers: Everyone
Self-RAG: Self-reflective Retrieval Augmented Generation
Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, Hannaneh Hajishirzi
- Instruction Workshop @ NeurIPS 2023
- Readers: Everyone
Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection
Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, Hannaneh Hajishirzi
- ICLR 2024 oral
- Readers: Everyone
UDAPDR: Unsupervised Domain Adaptation via LLM Prompting and Distillation of Rerankers
Jon Saad-Falcon, Omar Khattab, Keshav Santhanam, Radu Florian, Martin Franz, Salim Roukos, Avirup Sil, Md Arafat Sultan, Christopher Potts
- EMNLP 2023 Main
- Readers: Everyone
Capturing Row and Column Semantics in Transformer Based Question Answering over Tables
Michael Glass, MUSTAFA CANIM, Alfio Gliozzo, Saneem Ahmed Chemmengath, vishwajeet kumar, Rishav Chakravarti, Avirup Sil, Feifei Pan, Samarth Bharadwaj, NICOLAS RODOLFO FAUCEGLIA
- 03 Apr 2023
- OpenReview Archive Direct Upload
- Readers: Everyone

View all 17 publications

Co-Authors

View all 56 co-authors