Search Results for author:
Found 16 papers, 11 papers with code
Formal Mathematical Reasoning: A New Frontier in AI
AI for Mathematics (AI4Math) is not only intriguing intellectually but also crucial for AI-driven discovery in science, engineering, and beyond.
Data for Mathematical Copilots: Better Ways of Presenting Proofs for Machine Learning
The suite of datasets commonly used to train and evaluate the mathematical capabilities of AI-based mathematical copilots (primarily large language models) exhibit several shortcomings.
dafny-annotator: AI-Assisted Verification of Dafny Programs
Since this data-driven approach is hindered by the lack of large-scale training data, we propose a method for open-ended synthesis of new Dafny programs in a flexible pipeline where LLMs formulate high-level ideas, implement them, and incrementally propose changes to existing programs, which Dafny validates.
h4rm3l: A language for Composable Jailbreak Attack Synthesis
We demonstrate h4rm3l's efficacy by synthesizing a dataset of 2656 successful novel jailbreak attacks targeting 6 SOTA open-source and proprietary LLMs, and by benchmarking those models against a subset of these synthesized attacks.
MathCAMPS: Fine-grained Synthesis of Mathematical Problems From Human Curricula
Mathematical problem solving is an important skill for Large Language Models (LLMs), both as an important capability and a proxy for a range of reasoning abilities.
Learning Formal Mathematics From Intrinsic Motivation
We propose novel methods for hindsight relabeling on proof search trees to significantly improve the agent's sample efficiency in both tasks.
When Do Skills Help Reinforcement Learning? A Theoretical Analysis of Temporal Abstractions
Skills are temporal abstractions that are intended to improve reinforcement learning (RL) performance through hierarchical RL.
Hypothesis Search: Inductive Reasoning with Language Models
Inductive reasoning is a core problem-solving capacity: humans can identify underlying principles from a few examples, which robustly generalize to novel scenarios.
Certified Deductive Reasoning with Language Models
In experiments on PrOntoQA, ProofWriter and Syllogism Validity datasets, \textsc{LogicGuide} significantly improves the performance of GPT-3, GPT-3. 5 Turbo and LLaMA (accuracy gains up to 35\%), while drastically reducing \emph{content effects} -- the interference between unwanted prior assumptions and reasoning, which humans and language models suffer from.
Solving Math Word Problems by Combining Language Models With Symbolic Solvers
Automatically generating high-quality step-by-step solutions to math word problems has many applications in education.
Parsel: Algorithmic Reasoning with Language Models by Composing Decompositions
Despite recent success in large language model (LLM) reasoning, LLMs struggle with hierarchical multi-step reasoning tasks like generating complex programs.
Peano: Learning Formal Mathematical Reasoning
We explore this idea in a case study on 5 sections of beginning algebra on the Khan Academy platform.
LEMMA: Bootstrapping High-Level Mathematical Reasoning with Learned Symbolic Abstractions
Humans tame the complexity of mathematical reasoning by developing hierarchies of abstractions.
Synchromesh: Reliable code generation from pre-trained language models
Then, Synchromesh feeds the examples to a pre-trained language model and samples programs using Constrained Semantic Decoding (CSD): a general framework for constraining the output to a set of valid programs in the target language.
Open-domain clarification question generation without question examples
An overarching goal of natural language processing is to enable machines to communicate seamlessly with humans.
Contrastive Reinforcement Learning of Symbolic Reasoning Domains
Our results suggest new directions for reinforcement learning in symbolic domains, as well as applications to mathematics education.
