410 citations · 583 across the 38 of their papers we have counts for
47 papers
Preserving Reasoning Diversity in Reinforcement Learning with Verifiable Rewards via Adaptive Replay
Wen-Zhi Li, Sainyam Galhotra, Claire Cardie
Reinforcement Learning with Verifiable Rewards (RLVR) improves the reasoning capabilities of large language models, but often reduces the diversity of their reasoning behaviors. We…
Does On-Policy Distillation Need to Complete Every Rollout?
Zhengxin Zhang, Maosen Tang, Ning Wang +6
On-policy distillation (OPD) transfers teacher knowledge to a student through feedback on student-generated rollouts, but generating complete rollouts and computing per-token teach…
SALUS: Automated Auditing of NL-to-SQL Benchmarks through Weak Supervision of Multi-Agent Output
Shiyuan Zhou, Ashwin Gerard Colaco, Sainyam Galhotra +1
Natural language to SQL (NL-to-SQL) benchmarks are foundational to progress in data analysis research, yet recent work has shown that widely-used benchmarks contain significant ann…
Shifting Mechanisms: How Positional Encoding Choice Shapes In-Context Retrieval
Eric Enouen, Sainyam Galhotra
Language models increasingly use architectures that vary attention span and positional encoding across layers, such as applying RoPE with sliding-window attention and NoPE with glo…
HARP: Efficient Data Selection for Finetuning Large Language Models
Ning Wang, Zhengxin Zhang, Maosen Tang +3
Finetuning data selection requires balancing two competing goals: selecting examples that improve the downstream objective, and doing so without repeatedly finetuning models. Train…
How Far Are We From True Auto-Research?
Zhengxin Zhang, Ning Wang, Sainyam Galhotra +1
Recent auto-research systems can produce complete papers, but feasibility is not the same as quality, and the field still lacks a systematic study of how good agent-generated paper…
Trace-Level Analysis of Information Contamination in Multi-Agent Systems
Anna Mazhar, Huzaifa Suri, Sainyam Galhotra
Reasoning over heterogeneous artifacts (PDFs, spreadsheets, slide decks, etc.) increasingly occurs within structured agent workflows that iteratively extract, transform, and refere…
Towards Reliable Testing of Machine Unlearning
Anna Mazhar, Sainyam Galhotra
Machine learning components are now central to AI-infused software systems, from recommendations and code assistants to clinical decision support. As regulations and governance fra…
AutoPrunedRetriever: Persistent Reasoning Graphs for Efficient and Extensible Retrieval-Augmented Generation
Ning Wang, Kuanyan Zhu, Daniel Yuehwoon Yee +4
Retrieval-augmented generation (RAG) has become a standard approach for knowledge-intensive LLM tasks. Complex reasoning remains challenging because queries often require composing…
Metric -clustering using only Weak Comparison Oracles
Rahul Raychaudhury, Aryan Esmailpour, Sainyam Galhotra +1
Clustering is a fundamental primitive in unsupervised learning. However, classical algorithms for -clustering (such as -median and -means) assume access to exact pairwise…
Octopus: A Lightweight Entity-Aware System for Multi-Table Data Discovery and Cell-Level Retrieval
Wen-Zhi Li, Sainyam Galhotra
Tabular data constitute a dominant form of information in modern data lakes and repositories, yet discovering the relevant tables to answer user questions remains challenging. Exis…
MetaJoin: Adaptive Join Selections for Heterogeneous Tables
Ning Wang, Sainyam Galhotra
Joining heterogeneous tables requires different forms of correspondence, including exact agreement, syntactic transformation, semantic similarity, and entity-level matching. The ap…
CAFÉ: Causal Black-Box Testing of Machine Unlearning
Anna Mazhar, Sainyam Galhotra
Machine learning models are increasingly deployed as software components that must evolve as requirements change. When specific training records or features must no longer influenc…
Benchmarking Robust Aggregation in Decentralized Gradient Marketplaces
Zeyu Song, Sainyam Galhotra, Shagufta Mehnaz
The rise of distributed and privacy-preserving machine learning has sparked interest in decentralized gradient marketplaces, where participants trade intermediate artifacts like gr…
Debugging Concept Bottleneck Models through Removal and Retraining
Eric Enouen, Sainyam Galhotra
Concept Bottleneck Models (CBMs) use a set of human-interpretable concepts to predict the final task label, enabling domain experts to not only validate the CBM's predictions, but…
Towards General-Purpose Data Discovery: A Programming Languages Approach
Andrew Kang, Yashnil Saha, Sainyam Galhotra
Efficient and effective data discovery is critical for many modern applications in machine learning and data science. One major bottleneck to the development of a general-purpose d…
TQL: Towards Type-Driven Data Discovery
Andrew Kang, Sainyam Galhotra
Existing query languages for data discovery exhibit system-driven designs that emphasize database features and functionality over user needs. We propose a re-prioritization of the…
SIFOTL: A Principled, Statistically-Informed Fidelity-Optimization Method for Tabular Learning
Shubham Mohole, Sainyam Galhotra
Identifying the factors driving data shifts in tabular datasets is a significant challenge for analysis and decision support systems, especially those focusing on healthcare. Priva…
VeriMinder: Mitigating Analytical Vulnerabilities in NL2SQL
Shubham Mohole, Sainyam Galhotra
Application systems using natural language interfaces to databases (NLIDBs) have democratized data analysis. This positive development has also brought forth an urgent challenge to…
VERIRAG: A Post-Retrieval Auditing of Scientific Study Summaries
Shubham Mohole, Hongjun Choi, Shusen Liu +6
Can democratized information gatekeepers and community note writers effectively decide what scientific information to amplify? Lacking domain expertise, such gatekeepers rely on au…
A Theoretical Framework for Distribution-Aware Dataset Search
Aryan Esmailpour, Sainyam Galhotra, Rahul Raychaudhury +1
Effective data discovery is a cornerstone of modern data-driven decision-making. Yet, identifying datasets with specific distributional characteristics, such as percentiles or pref…
Fair and Actionable Causal Prescription Ruleset
Benton Li, Nativ Levy, Brit Youngmann +2
Prescriptions, or actionable recommendations, are commonly generated across various fields to influence key outcomes such as improving public health, enhancing economic policies, o…
Intervention and Conditioning in Causal Bayesian Networks
Sainyam Galhotra, Joseph Y. Halpern
Causal models are crucial for understanding complex systems and identifying causal relationships among variables. Even though causal models are extremely popular, conditional proba…
Faster Algorithms for Fair Max-Min Diversification in
Yash Kurkure, Miles Shamo, Joseph Wiseman +2
The task of extracting a diverse subset from a dataset, often referred to as maximum diversification, plays a pivotal role in various real-world applications that have far-reaching…