author

Harit Vishwakarma

Research Intern
,
Snorkel AI

Harit Vishwakarma is a Research Intern at Snorkel AI, focusing on evaluating and improving the reasoning capabilities of large language models. He recently completed his PhD in Computer Science at the University of Wisconsin–Madison. His research centers on studying and developing methods for reliable inference and leveraging them for automated data labeling and enhancing performance at test time. Next, he is off to the University of Oxford for a postdoc.

The latest from Harit

Learning from Less: Measuring the Effectiveness of RLVR in Low Data and Compute Regimes
Fine-tuning Large Language Models (LLMs) typically relies on large quantities of high-quality annotated data, or questions with well-defined ground truth answers in the case of Reinforcement Learning with Verifiable Rewards (RLVR). While previous work has explored the benefits to model reasoning capabilities by scaling both data and compute used for RLVR, these results lack applicability in many real-world settings where annotated data and accessible compute may be scarce. In this work, we present a comprehensive empirical study of open-source Small Language Model (SLM) performance after RLVR in low data regimes. Across three novel datasets covering number counting problems, graph reasoning,...
Research Paper
Accepted to MLSys 2026
Learning from Less: Measuring the Effectiveness of RLVR in Low Data and Compute Regimes

Fine-tuning Large Language Models (LLMs) typically relies on large quantities of high-quality annotated data, or questions with well-defined ground truth answers in the case of Reinforcement Learning with Verifiable Rewards (RLVR). While previous work has explored the benefits to model reasoning capabilities by scaling both data and compute used for RLVR, these results lack applicability in many real-world settings where…

Apr 20, 2026 •

Justin Bauer, Thomas Walshe, Derek Pham, Harit Vishwakarma + 3 more

Learn more about Learning from Less: Measuring the Effectiveness of RLVR in Low Data and Compute Regimes
Automating benchmark design
The rapid progress and widespread deployment of LLMs and LLM-powered agents has outpaced our ability to evaluate them. Hand-crafted, static benchmarks are the primary tool for assessing model capabilities, but these quickly become saturated. In contrast, dynamic benchmarks evolve alongside the models they evaluate, but are expensive to create and continuously update. To address these challenges, we develop BeTaL (Benchmark Tuning with an LLM-in-the-loop), a framework that leverages environment design principles to automate the process of dynamic benchmark design. BeTaL works by parameterizing key design choices in base benchmark templates and uses LLMs to reason through the resulting parameter space...
Research Paper
Automating benchmark design

The rapid progress and widespread deployment of LLMs and LLM-powered agents has outpaced our ability to evaluate them. Hand-crafted, static benchmarks are the primary tool for assessing model capabilities, but these quickly become saturated. In contrast, dynamic benchmarks evolve alongside the models they evaluate, but are expensive to create and continuously update. To address these challenges, we develop BeTaL (Benchmark…

Learn more about Automating benchmark design
Introducing SnorkelSpatial
Blog
Introducing SnorkelSpatial

A procedurally generated and programmatically verified benchmark for evaluating spatial reasoning capabilities in LLMs Large language models (LLMs) are showing remarkable results on solving complex reasoning problems across domains—from mathematical proofs and logical puzzles to graduate-level science and engineering questions. On the other hand, their spatial reasoning capabilities are less understood, even though such reasoning underlies many everyday tasks. We…

Oct 24, 2025 •
Learn more about Introducing SnorkelSpatial
Rethinking Confidence and Thresholds in Pseudolabeling-based SSL
Modern semi-supervised learning (SSL) methods rely on pseudolabeling and consistency regularization. Pseudolabeling is typically performed by comparing the model’s confidence scores and a predefined threshold. While several heuristics have been proposed to improve threshold selection, the underlying issues of overconfidence and miscalibration in confidence scores remain largely unaddressed, leading to inaccurate pseudolabels, degraded test accuracy, and prolonged training. We take a first-principles approach to learn confidence scores and thresholds with an explicit knob for error. This flexible framework addresses the fundamental question of optimal scores and threshold selection in pseudolabeling. Moreover, it gives practitioners a principled way to control the...
Research Paper
Accepted to ICML 2025
Rethinking Confidence and Thresholds in Pseudolabeling-based SSL

Modern semi-supervised learning (SSL) methods rely on pseudolabeling and consistency regularization. Pseudolabeling is typically performed by comparing the model’s confidence scores and a predefined threshold. While several heuristics have been proposed to improve threshold selection, the underlying issues of overconfidence and miscalibration in confidence scores remain largely unaddressed, leading to inaccurate pseudolabels, degraded test accuracy, and prolonged training. We take…

Jul 31, 2025 •

Harit Vishwakarma, Yi Chen, Srinath Namburi, Sui Jiet Tay + 2 more

Learn more about Rethinking Confidence and Thresholds in Pseudolabeling-based SSL
Pearls from Pebbles: Improved Confidence Functions for Auto-labeling
Auto-labeling is an important family of techniques that produce labeled training sets with minimum manual labeling. A prominent variant, threshold-based auto-labeling (TBAL), works by finding a threshold on a model’s confidence scores above which it can accurately label unlabeled data points. However, many models are known to produce overconfident scores, leading to poor TBAL performance. While a natural idea is to apply off-the-shelf calibration methods to alleviate the overconfidence issue, such methods still fall short. Rather than experimenting with ad-hoc choices of confidence functions, we propose a framework for studying the optimal TBAL confidence function. We develop a tractable version...
Research Paper
Pearls from Pebbles: Improved Confidence Functions for Auto-labeling

Auto-labeling is an important family of techniques that produce labeled training sets with minimum manual labeling. A prominent variant, threshold-based auto-labeling (TBAL), works by finding a threshold on a model’s confidence scores above which it can accurately label unlabeled data points. However, many models are known to produce overconfident scores, leading to poor TBAL performance. While a natural idea is…

Sep 18, 2024 •

Harit Vishwakarma, Yi Chen, Sui Jiet Tay, Satya Sai Srinath Namburi + 2 more

Learn more about Pearls from Pebbles: Improved Confidence Functions for Auto-labeling
OTTER: Improving Zero-Shot Classification via Optimal Transport
Popular zero-shot models suffer due to artifacts inherited from pretraining. A particularly detrimental artifact, caused by unbalanced web-scale pretraining data, is mismatched label distribution. Existing approaches that seek to repair the label distribution are not suitable in zero-shot settings, as they have incompatible requirements such as access to labeled downstream task data or knowledge of the true label balance in the pretraining distribution. We sidestep these challenges and introduce a simple and lightweight approach to adjust pretrained model predictions via optimal transport. Our technique requires only an estimate of the label distribution of a downstream task. Theoretically, we characterize the...
Research Paper
OTTER: Improving Zero-Shot Classification via Optimal Transport

Popular zero-shot models suffer due to artifacts inherited from pretraining. A particularly detrimental artifact, caused by unbalanced web-scale pretraining data, is mismatched label distribution. Existing approaches that seek to repair the label distribution are not suitable in zero-shot settings, as they have incompatible requirements such as access to labeled downstream task data or knowledge of the true label balance in…

Sep 18, 2024 •

Changho Shin, Jitian Zhao, Sonia Cromp, Harit Vishwakarma + 1 more

Learn more about OTTER: Improving Zero-Shot Classification via Optimal Transport
Promises and Pitfalls of Threshold-based Auto-labeling
Creating large-scale high-quality labeled datasets is a major bottleneck in supervised machine learning workflows. Threshold-based auto-labeling (TBAL), where validation data obtained from humans is used to find a confidence threshold above which the data is machine-labeled, reduces reliance on manual annotation. TBAL is emerging as a widely-used solution in practice. Given the long shelf-life and diverse usage of the resulting datasets, understanding when the data obtained by such auto-labeling systems can be relied on is crucial. This is the first work to analyze TBAL systems and derive sample complexity bounds on the amount of human-labeled validation data required for guaranteeing...
Research Paper
Promises and Pitfalls of Threshold-based Auto-labeling

Creating large-scale high-quality labeled datasets is a major bottleneck in supervised machine learning workflows. Threshold-based auto-labeling (TBAL), where validation data obtained from humans is used to find a confidence threshold above which the data is machine-labeled, reduces reliance on manual annotation. TBAL is emerging as a widely-used solution in practice. Given the long shelf-life and diverse usage of the resulting…

Jan 11, 2024 •

Harit Vishwakarma, Heguang Lin, Frederic Sala, Ramya Korlakai Vinayak

Learn more about Promises and Pitfalls of Threshold-based Auto-labeling
Train ‘n Trade: Foundations of Parameter Markets
Organizations typically train large models individually. This is costly and time-consuming, particularly for large-scale foundation models. Such vertical production is known to be suboptimal. Inspired by this economic insight, we ask whether it is possible to leverage others’ expertise by trading the constituent parts in models, i.e., sets of weights, as if they were market commodities. While recent advances in aligning and interpolating models suggest that doing so may be possible, a number of fundamental questions must be answered to create viable parameter markets. In this work, we address these basic questions, propose a framework containing the infrastructure necessary for...
Research Paper
Train ‘n Trade: Foundations of Parameter Markets

Organizations typically train large models individually. This is costly and time-consuming, particularly for large-scale foundation models. Such vertical production is known to be suboptimal. Inspired by this economic insight, we ask whether it is possible to leverage others’ expertise by trading the constituent parts in models, i.e., sets of weights, as if they were market commodities. While recent advances in…

Dec 07, 2023 •

Tzu-Heng Huang, Harit Vishwakarma, Frederic Sala

Learn more about Train ‘n Trade: Foundations of Parameter Markets
Good Data from Bad Models: Foundations of Threshold-based Auto-labeling
Creating large-scale high-quality labeled datasets is a major bottleneck in supervised machine learning workflows. Auto-labeling systems are a promising way to reduce reliance on manual labeling for dataset construction. Threshold-based auto-labeling, where validation data obtained from humans is used to find a threshold for confidence above which the data is machine-labeled, is emerging as a popular solution used widely in practice [SGT22, QCG20, SS22]. Given the long shelf-life and diverse usage of the resulting datasets, understanding when the data obtained by such auto-labeling systems can be relied on is crucial. In this work, we analyze threshold-based auto-labeling systems and derive...
Research Paper
Good Data from Bad Models: Foundations of Threshold-based Auto-labeling

Creating large-scale high-quality labeled datasets is a major bottleneck in supervised machine learning workflows. Auto-labeling systems are a promising way to reduce reliance on manual labeling for dataset construction. Threshold-based auto-labeling, where validation data obtained from humans is used to find a threshold for confidence above which the data is machine-labeled, is emerging as a popular solution used widely in…

Oct 20, 2023 •

Harit Vishwakarma, Heguang Lin, Frederic Sala, Ramya Korlakai Vinayak

Learn more about Good Data from Bad Models: Foundations of Threshold-based Auto-labeling
1 2

For models that need to be right. Not just good enough.