Papers by Manan Roy Choudhury
TABARD: A Novel Benchmark for Tabular Anomaly Analysis, Reasoning and Detection (2025.findings-emnlp)
Copied to clipboard
Manan Roy Choudhury, Anirudh Iyengar Kaniyar Narayana Iyengar, Shikhhar Siingh, Sugeeth Puranam, Vivek Gupta
| Challenge: | a new benchmark is constructed to evaluate the accuracy of large language models for tabular data . the benchmark uses direct, indirect, and Chain-of-Thought prompting . |
| Approach: | They propose a framework that uses prompting, self-verification and constraint-based rule execution to improve accuracy. |
| Outcome: | The proposed framework significantly improves accuracy and recall in tabular data. |
REaR : Retrieve, Expand and Refine for Effective Multitable Retrieval (2026.acl-long)
Copied to clipboard
| Challenge: | REaR is retriever-agnostic and improves dense/ sparse retrievers on complex table QA datasets. |
| Approach: | a new framework separates semantic relevance from structural joinability for efficient multi-table retrieval. adam scott and eric liu introduce REaR, a three-stage, LLM-free framework. |
| Outcome: | a new framework improves retrieval quality and performance on complex table QA datasets . it separates semantic relevance from structural joinability and prunes weakly related candidates . the framework is retriever-agnostic and delivers performance competitive with state-of-the-art LLM-augmented retrieval systems . |
Better Call CLAUSE: A Discrepancy Benchmark for Auditing LLMs Legal Reasoning Capabilities (2026.findings-eacl)
Copied to clipboard
| Challenge: | Existing evaluation methods fail to probe fragile reasoning capabilities of large language models (LLMs) a single undetected defect can have catastrophic consequences, highlighting the need for a new class of benchmarks to stress-test their reliability against nuanced contractual flaws. |
| Approach: | They propose a benchmark to evaluate the fragility of an LLM’s legal reasoning by producing over 7500 real-world perturbed contracts from foundational datasets like CUAD and ContractNLI. |
| Outcome: | The proposed benchmark evaluates LLMs' ability to detect and reason about fine-grained discrepancies from over 7500 real-world perturbed contracts from foundational datasets like CUAD and ContractNLI. |
FD-NL2SQL: Feedback-Driven Clinical NL2SQL that Improves with Use (2026.acl-demo)
Copied to clipboard
Suparno Roy Chowdhury, Tejas Anvekar, Manan Roy Choudhury, Muhammad Ali Khan, Kaneez Zahra Rubab Khakwani, M Bassam Sonbol, Irbaz Bin Riaz, Vivek Gupta
| Challenge: | Clinical trial databases are central to modern oncology research and drug development. |
| Approach: | FD-NL2SQL is a schema-aware clinical NL2sql assistant for SQLite-based oncology databases . it decomposes a natural-language question into predicate-level sub-questions and synthesizes executable SQL . |
| Outcome: | FD-NL2SQL synthesizes SQL based on decomposition, retrieved exemplars, and schema . clinical trial databases are central to modern oncology research and drug development . |