01TurnBenchSpoken dialogue
Preprint · 2026
TurnBench: A Multi-Domain Benchmark for Turn-Taking Dynamics in Spoken Dialogue
Knowing when to speak, listen, or yield: evaluating turn-taking across six styles of natural conversation.
Researcher at Sesame / San Francisco
Satyapriya
Krishna.
Building frontier intelligence.
I’m Satya. I train frontier AI models to tackle incredibly complex tasks. I’m currently a researcher at Sesame.
Along the way
SesameGoogle DeepMindAmazonHarvardCarnegie Mellon
01 / UPDATES
A new chapter.
A new chapter in
frontier intelligence.
I’ve joined Sesame, where I’m working on building the best voice model.
Meet SesameIntroducing TurnBench: a benchmark, dataset, and leaderboard for turn-taking in spoken dialogue.
Released D-REX, a benchmark for detecting deceptive reasoning in language models.
Harvard PhD thesis: From Understanding to Improving Artificial Intelligence: New Frontiers in Machine Learning Explanations.
Introduced FRAMES, a benchmark for factuality, retrieval, and reasoning. Published at NAACL 2025.
Earlier news
Teaching Fellow for COMPSCI 236R: Topics at the Interface between Computer Science and Economics.
Amazon Science highlighted my contributions to trustworthy machine learning at Alexa AI.
Presented The Disagreement Problem at the TRAIT Workshop at CHI. Two papers on algorithmic fairness accepted at ACL: paper one and paper two.
Released The Disagreement Problem, later published in TMLR. Covered by Fortune and Analytics India Magazine. Received the Nicole A. Chen and Karina A. Chen Graduate Student Research Fellowship.
Joined Harvard SEAS as a Computer Science PhD student.
Does Robustness Improve Fairness? accepted at Findings of ACL 2021.
VentureBeat covered BOLD, our benchmark for measuring bias in open-ended language generation.
ADePT, our work on private text transformation, accepted at EACL 2021.
Announced BOLD, a fairness benchmark for open-ended language generation, presented at FAccT 2021.
02 / RESEARCH
All publications on Scholar Selected work.
Improving how models reason. Understanding their behavior. Making frontier intelligence more useful, reliable, and worthy of trust.
02FRAMESRetrieval & reasoning
NAACL 2025
Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation
Evaluating factuality, retrieval, and reasoning together, with questions that require information from multiple sources.
03D-REXTrustworthy language models
Preprint · 2025
D-REX: A Benchmark for Detecting Deceptive Reasoning in Large Language Models
Detecting the gap between apparently benign answers and deceptive reasoning in language models.
04TalkToModelInteractive explainability
Nature Machine Intelligence · 2023
Explaining machine learning models with interactive natural language conversations using TalkToModel
Understanding model predictions through a conversation: explanations, data analysis, and follow-up questions in natural language.
More selected publications 10
05AMPLIFYLearning from explanations
NeurIPS 2023
Post Hoc Explanations of Language Models Can Improve Language Models
Turning model explanations into natural language rationales that help language models correct their mistakes.
06Model safety
ACL 2026
ARES: Adaptive Red-Teaming and End-to-End Repair of Policy-Reward System
Finding safety failures shared by a language model and its reward model, then repairing both.
07Unlearning & alignment
ACL 2026
From Narrow Unlearning to Emergent Misalignment in LLMs
Studying how removing refusals in one domain can weaken safety in other domains.
08Evaluation & security
Findings of ACL 2026
AutoSUIT Bench - Automated Security UnIt Test Benchmark for LLM Coding
An automatically validated benchmark measuring the security of LLM-generated code across software weakness categories.
09Understanding alignment
COLM 2025
Insights from the Inverse: Reconstructing LLM Training Goals Through Inverse Reinforcement Learning
Recovering reward functions from aligned language models to investigate what their training objectives encode.
10Explainability
TMLR 2024
The Disagreement Problem in Explainable Machine Learning: A Practitioner's Perspective
Measuring how explanation methods disagree, and how practitioners navigate conflicting explanations.
11Truthfulness
ICML 2024
Understanding the Effects of Iterative Prompting on Truthfulness
Studying when repeated prompting reduces truthfulness and calibration, and how prompting strategies can help.
12Open evaluation
NeurIPS 2022 · Datasets & Benchmarks
OpenXAI: Towards a Transparent Evaluation of Model Explanations
Tools for comparing the faithfulness, stability, and fairness of model explanations.
13Fairness
ACM FAccT 2021
BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation
A dataset and evaluation metrics for measuring social biases in open-ended language generation.
14Privacy
EACL 2021
ADePT: Auto-encoder based Differentially Private Text Transformation
Exploring text transformations designed to protect privacy while retaining useful semantic information.
03 / ABOUTResearch meets
Research meets
the real world.
I completed my PhD at Harvard’s School of Engineering and Applied Sciences, advised by Hima Lakkaraju and Finale Doshi-Velez. My research focused on understanding and improving the trustworthy aspects of generative models. I also collaborated with Sameer Singh at UC Irvine and Steven Wu at Carnegie Mellon.
Previously, I worked at Google DeepMind and Meta FAIR, and led research initiatives across AWS, Alexa, and Amazon Search. At Carnegie Mellon, I studied conversational agents and reinforcement learning.
PhD · Computer ScienceHarvard University
School of Engineering and Applied Sciences
Master’s degreeCarnegie Mellon University
School of Computer Science
Doctoral thesis: From Understanding to Improving Artificial Intelligence: New Frontiers in Machine Learning Explanations.
View my CVAcademic service & community
- Co-President · Harvard SEAS Graduate Council, 2022
- Program Committee · ICML Workshop on Human-Machine Collaboration and Teaming, 2022
- Reviewer · NeurIPS Datasets and Benchmarks, 2021–2022; NeurIPS Main Conference, 2022; AAAI, 2021
- Organizing Committee · Workshop on Trustworthy NLP at NAACL, 2021
- Student Volunteer Award · ACL, 2022
- Volunteer · ACM FAccT, 2022