21 citations · 68 across the 22 of their papers we have counts for
21 papers
QuasiMoTTo: Quasi-Monte Carlo Test-Time Scaling
Michael Y. Li, Anthony Zhan, Kanishk Gandhi +2
Scaling inference compute, by generating many parallel attempts per problem, is a costly but reliable lever for improving language model capabilities. By default these attempts are…
Learning Next Action Predictors from Human-Computer Interaction
Omar Shaikh, Valentin Teutschbein, Kanishk Gandhi +8
Truly proactive AI systems must anticipate what we will do next. This foresight demands far richer information than the sparse signals we type into our prompts -- it demands reason…
Endless Terminals: Scaling RL Environments for Terminal Agents
Kanishk Gandhi, Shivam Garg, Noah D. Goodman +1
Environments are the bottleneck for self-improving agents. Current terminal benchmarks were built for evaluation, not training; reinforcement learning requires a scalable pipeline,…
Learning to Simulate Human Dialogue
Kanishk Gandhi, Agam Bhatia, Noah D. Goodman
To predict what someone will say is to model how they think. We study this through next-turn dialogue prediction: given a conversation, predict the next utterance produced by a per…
Scaling up the think-aloud method
Daniel Wurgaft, Ben Prystawski, Kanishk Gandhi +3
The think-aloud method, where participants voice their thoughts as they solve a task, is a valuable source of rich data about human reasoning processes. Yet, it has declined in pop…
Non-literal Understanding of Number Words by Language Models
Polina Tsvilodub, Kanishk Gandhi, Haoran Zhao +3
Humans naturally interpret numbers non-literally, effortlessly combining context, world knowledge, and speaker intent. We investigate whether large language models (LLMs) interpret…
BoxingGym: Benchmarking Progress in Automated Experimental Design and Model Discovery
Kanishk Gandhi, Michael Y. Li, Lyle Goodyear +5
Understanding the world and explaining it with scientific theories is a central aspiration of artificial intelligence research. Proposing theories, designing experiments to test th…
Human-like Affective Cognition in Foundation Models
Kanishk Gandhi, Zoe Lynch, Jan-Philipp Fränken +5
Understanding emotions is fundamental to human interaction and experience. Humans easily infer emotions from situations or facial expressions, situations from emotions, and do a va…
PERSONA: A Reproducible Testbed for Pluralistic Alignment
Louis Castricato, Nathan Lile, Rafael Rafailov +2
The rapid advancement of language models (LMs) necessitates robust alignment with diverse user values. However, current preference optimization approaches often fail to capture the…
Psychometric Alignment: Capturing Human Knowledge Distributions via Language Models
Joy He-Yueya, Wanjing Anya Ma, Kanishk Gandhi +3
Language models (LMs) are increasingly used to simulate human-like responses in scenarios where accurately mimicking a population's behavior can guide decision-making, such as in d…
Self-Supervised Alignment with Mutual Information: Learning to Follow Principles without Preference Labels
Jan-Philipp Fränken, Eric Zelikman, Rafael Rafailov +3
When prompting a language model (LM), users often expect the model to adhere to a set of behavioral principles across diverse tasks, such as producing insightful content while avoi…
Procedural Dilemma Generation for Evaluating Moral Reasoning in Humans and Language Models
Jan-Philipp Fränken, Kanishk Gandhi, Tori Qiu +3
As AI systems like language models are increasingly integrated into decision-making processes affecting people's lives, it's critical to ensure that these systems have sound moral…
Stream of Search (SoS): Learning to Search in Language
Kanishk Gandhi, Denise Lee, Gabriel Grand +4
Language models are rarely shown fruitful mistakes while training. They then struggle to look beyond the next token, suffering from a snowballing of errors and struggling to predic…
Social Contract AI: Aligning AI Assistants with Implicit Group Norms
Jan-Philipp Fränken, Sam Kwok, Peixuan Ye +6
We explore the idea of aligning an AI assistant by inverting a model of users' (unknown) preferences from observed interactions. To validate our proposal, we run proof-of-concept s…
A Fourier Neural Operator Approach for Modelling Exciton-Polariton Condensate Systems
Yuan Wang, Surya T. Sathujoda, Krzysztof Sawicki +3
A plethora of next-generation all-optical devices based on exciton-polaritons have been proposed in latest years, including prototypes of transistors, switches, analogue quantum si…
Understanding Social Reasoning in Language Models with Language Models
Kanishk Gandhi, Jan-Philipp Fränken, Tobias Gerstenberg +1
As Large Language Models (LLMs) become increasingly integrated into our everyday lives, understanding their ability to comprehend human mental states becomes critical for ensuring…
Certified Deductive Reasoning with Language Models
Gabriel Poesia, Kanishk Gandhi, Eric Zelikman +1
Language models often achieve higher accuracy when reasoning step-by-step in complex tasks. However, even when arriving at a correct final answer, their rationales are often logica…
Strategic Reasoning with Language Models
Kanishk Gandhi, Dorsa Sadigh, Noah D. Goodman
Strategic reasoning enables agents to cooperate, communicate, and compete with other agents in diverse situations. Existing approaches to solving strategic games rely on extensive…
Eliciting Compatible Demonstrations for Multi-Human Imitation Learning
Kanishk Gandhi, Siddharth Karamcheti, Madeline Liao +1
Imitation learning from human-provided demonstrations is a strong approach for learning policies for robot manipulation. While the ideal dataset for imitation learning is homogenou…
Baby Intuitions Benchmark (BIB): Discerning the goals, preferences, and actions of others
Kanishk Gandhi, Gala Stojnic, Brenden M. Lake +1
To achieve human-like common sense about everyday life, machine learning systems must understand and reason about the goals, preferences, and actions of other agents in the environ…
Mutual exclusivity as a challenge for deep neural networks
Kanishk Gandhi, Brenden M. Lake
Strong inductive biases allow children to learn in fast and adaptable ways. Children use the mutual exclusivity (ME) bias to help disambiguate how words map to referents, assuming…