421 citations · 695 across the 17 of their papers we have counts for
17 papers
Shoot First, Ask Questions Later? Building Rational Agents that Explore and Act Like People
Gabriel Grand, Valerio Pepe, Jacob Andreas +1
Many emerging applications of AI--from scientific discovery to medical diagnosis--require agents to seek information strategically: forming hypotheses, asking targeted questions, a…
Syntactic and Semantic Control of Large Language Models via Sequential Monte Carlo
João Loula, Benjamin LeBrun, Li Du +12
A wide range of LM applications require generating text that conforms to syntactic or semantic constraints. Imposing such constraints can be naturally framed as probabilistic condi…
Self-Steering Language Models
Gabriel Grand, Joshua B. Tenenbaum, Vikash K. Mansinghka +2
While test-time reasoning enables language models (LMs) to tackle complex tasks, searching or planning in natural language can be slow, costly, and error-prone. But even when LMs s…
Elements of World Knowledge (EWoK): A Cognition-Inspired Framework for Evaluating Basic World Knowledge in Language Models
Anna A. Ivanova, Aalok Sathe, Benjamin Lipkin +17
The ability to build and reason about models of the world is essential for situated language understanding. But evaluating world modeling capabilities in modern AI systems -- espec…
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…
Loose LIPS Sink Ships: Asking Questions in Battleship with Language-Informed Program Sampling
Gabriel Grand, Valerio Pepe, Jacob Andreas +1
Questions combine our mastery of language with our remarkable facility for reasoning about uncertainty. How do people navigate vast hypothesis spaces to pose informative questions…
LILO: Learning Interpretable Libraries by Compressing and Documenting Code
Gabriel Grand, Lionel Wong, Maddy Bowers +4
While large language models (LLMs) now excel at code generation, a key aspect of software development is the art of refactoring: consolidating code into libraries of reusable and r…
From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thought
Lionel Wong, Gabriel Grand, Alexander K. Lew +4
How does language inform our downstream thinking? In particular, how do humans make meaning from language--and how can we leverage a theory of linguistic meaning to build machines…
Sequential Monte Carlo Steering of Large Language Models using Probabilistic Programs
Alexander K. Lew, Tan Zhi-Xuan, Gabriel Grand +1
Even after fine-tuning and reinforcement learning, large language models (LLMs) can be difficult, if not impossible, to control reliably with prompts alone. We propose a new infere…
Evaluating statistical language models as pragmatic reasoners
Benjamin Lipkin, Lionel Wong, Gabriel Grand +1
The relationship between communicated language and intended meaning is often probabilistic and sensitive to context. Numerous strategies attempt to estimate such a mapping, often l…
Top-Down Synthesis for Library Learning
Matthew Bowers, Theo X. Olausson, Lionel Wong +4
This paper introduces corpus-guided top-down synthesis as a mechanism for synthesizing library functions that capture common functionality from a corpus of programs in a domain spe…
ChemBERTa-2: Towards Chemical Foundation Models
Walid Ahmad, Elana Simon, Seyone Chithrananda +2
Large pretrained models such as GPT-3 have had tremendous impact on modern natural language processing by leveraging self-supervised learning to learn salient representations that…
Identifying concept libraries from language about object structure
Catherine Wong, William P. McCarthy, Gabriel Grand +5
Our understanding of the visual world goes beyond naming objects, encompassing our ability to parse objects into meaningful parts, attributes, and relations. In this work, we lever…
ChemBERTa: Large-Scale Self-Supervised Pretraining for Molecular Property Prediction
Seyone Chithrananda, Gabriel Grand, Bharath Ramsundar
GNNs and chemical fingerprints are the predominant approaches to representing molecules for property prediction. However, in NLP, transformers have become the de-facto standard for…
Adversarial Regularization for Visual Question Answering: Strengths, Shortcomings, and Side Effects
Gabriel Grand, Yonatan Belinkov
Visual question answering (VQA) models have been shown to over-rely on linguistic biases in VQA datasets, answering questions "blindly" without considering visual context. Adversar…
On the Flip Side: Identifying Counterexamples in Visual Question Answering
Gabriel Grand, Aron Szanto, Yoon Kim +1
Visual question answering (VQA) models respond to open-ended natural language questions about images. While VQA is an increasingly popular area of research, it is unclear to what e…
Semantic projection: recovering human knowledge of multiple, distinct object features from word embeddings
Gabriel Grand, Idan Asher Blank, Francisco Pereira +1
The words of a language reflect the structure of the human mind, allowing us to transmit thoughts between individuals. However, language can represent only a subset of our rich and…