Search Results for author:
Found 13 papers, 10 papers with code
Stream of Search (SoS): Learning to Search in Language
In this paper, we show how language models can be taught to search by representing the process of search in language, as a flattened string -- a stream of search (SoS).
Loose LIPS Sink Ships: Asking Questions in Battleship with Language-Informed Program Sampling
Questions combine our mastery of language with our remarkable facility for reasoning about uncertainty.
LILO: Learning Interpretable Libraries by Compressing and Documenting Code
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 readable programs.
From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thought
Our architecture integrates two computational tools that have not previously come together: we model thinking with probabilistic programs, an expressive representation for commonsense reasoning; and we model meaning construction with large language models (LLMs), which support broad-coverage translation from natural language utterances to code expressions in a probabilistic programming language.
Sequential Monte Carlo Steering of Large Language Models using Probabilistic Programs
Even after fine-tuning and reinforcement learning, large language models (LLMs) can be difficult, if not impossible, to control reliably with prompts alone.
Evaluating statistical language models as pragmatic reasoners
These results inform the inferential capacity of statistical language models, and their use in pragmatic and semantic parsing applications.
Top-Down Synthesis for Library Learning
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 specific language (DSL).
ChemBERTa-2: Towards Chemical Foundation Models
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 can be used to readily finetune on a wide variety of downstream tasks.
Ranked #2 on
Molecular Property Prediction
on Clearance
Identifying concept libraries from language about object structure
Our understanding of the visual world goes beyond naming objects, encompassing our ability to parse objects into meaningful parts, attributes, and relations.
ChemBERTa: Large-Scale Self-Supervised Pretraining for Molecular Property Prediction
GNNs and chemical fingerprints are the predominant approaches to representing molecules for property prediction.
Adversarial Regularization for Visual Question Answering: Strengths, Shortcomings, and Side Effects
Visual question answering (VQA) models have been shown to over-rely on linguistic biases in VQA datasets, answering questions "blindly" without considering visual context.
On the Flip Side: Identifying Counterexamples in Visual Question Answering
Visual question answering (VQA) models respond to open-ended natural language questions about images.
Semantic projection: recovering human knowledge of multiple, distinct object features from word embeddings
Because related words appear in similar contexts, such spaces - called "word embeddings" - can be learned from patterns of lexical co-occurrences in natural language.
