Search Results for author:
Found 35 papers, 27 papers with code
STEER: Unified Style Transfer with Expert Reinforcement
We propose STEER: Unified Style Transfer with Expert Reinforcement, a unified frame-work developed to overcome the challenge of limited parallel data for style transfer.
LLMSTEP: LLM proofstep suggestions in Lean
LLMSTEP is a Lean 4 tactic that sends a user's proof state to a server hosting a language model.
Llemma: An Open Language Model For Mathematics
We present Llemma, a large language model for mathematics.
Ranked #5 on
Automated Theorem Proving
on miniF2F-test
Faith and Fate: Limits of Transformers on Compositionality
We formulate compositional tasks as computation graphs to systematically quantify the level of complexity, and break down reasoning steps into intermediate sub-procedures.
Inference-Time Policy Adapters (IPA): Tailoring Extreme-Scale LMs without Fine-tuning
In particular, tailoring GPT-2 with IPA can outperform GPT-3, while tailoring GPT- 3 with IPA brings a major performance boost over GPT-3 (and sometimes even over GPT-4).
Self-Refine: Iterative Refinement with Self-Feedback
Motivated by how humans refine their written text, we introduce Self-Refine, an approach for improving initial outputs from LLMs through iterative feedback and refinement.
MAUVE Scores for Generative Models: Theory and Practice
We present MAUVE, a family of comparison measures between pairs of distributions such as those encountered in the generative modeling of text or images.
A Survey of Deep Learning for Mathematical Reasoning
Mathematical reasoning is a fundamental aspect of human intelligence and is applicable in various fields, including science, engineering, finance, and everyday life.
Lila: A Unified Benchmark for Mathematical Reasoning
Mathematical reasoning skills are essential for general-purpose intelligent systems to perform tasks from grocery shopping to climate modeling.
Ranked #1 on
Mathematical Reasoning
on Lila (OOD)
Generating Sequences by Learning to Self-Correct
Sequence generation applications require satisfying semantic constraints, such as ensuring that programs are correct, using certain keywords, or avoiding undesirable content.
Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs
In this work, we introduce Draft, Sketch, and Prove (DSP), a method that maps informal proofs to formal proof sketches, and uses the sketches to guide an automated prover by directing its search to easier sub-problems.
Ranked #3 on
Automated Theorem Proving
on miniF2F-valid
(Pass@100 metric)
Rainier: Reinforced Knowledge Introspector for Commonsense Question Answering
Our work is the first to report that knowledge generated by models that are orders of magnitude smaller than GPT-3, even without direct supervision on the knowledge itself, can exceed the quality of commonsense knowledge elicited from GPT-3.
Quark: Controllable Text Generation with Reinforced Unlearning
Large-scale language models often learn behaviors that are misaligned with user expectations.
NaturalProver: Grounded Mathematical Proof Generation with Language Models
Theorem proving in natural mathematical language - the mixture of symbolic and natural language used by humans - plays a central role in mathematical advances and education, and tests aspects of reasoning that are core to intelligence.
Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations
Despite their impressive capabilities, large pre-trained language models (LMs) struggle with consistent reasoning; recently, prompting LMs to generate explanations that self-guide the inference has emerged as a promising direction to amend this.
COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamics
Many applications of text generation require incorporating different constraints to control the semantics or style of generated text.
NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristics
To enable constrained generation, we build on NeuroLogic decoding (Lu et al., 2021), combining its flexibility in incorporating logical constraints with A*esque estimates of future constraint satisfaction.
Ranked #1 on
Text Generation
on ROCStories
Prompt Waywardness: The Curious Case of Discretized Interpretation of Continuous Prompts
Fine-tuning continuous prompts for target tasks has recently emerged as a compact alternative to full model fine-tuning.
Generated Knowledge Prompting for Commonsense Reasoning
It remains an open question whether incorporating external knowledge benefits commonsense reasoning while maintaining the flexibility of pretrained sequence models.
Symbolic Knowledge Distillation: from General Language Models to Commonsense Models
We apply this to the ATOMIC resource, and share our new symbolic knowledge graph and commonsense models.
Symbolic Brittleness in Sequence Models: on Systematic Generalization in Symbolic Mathematics
Neural sequence models trained with maximum likelihood estimation have led to breakthroughs in many tasks, where success is defined by the gap between training and test performance.
Out-of-Distribution Generalization
Systematic Generalization
+1
Divergence Frontiers for Generative Models: Sample Complexity, Quantization Effects, and Frontier Integrals
The spectacular success of deep generative models calls for quantitative tools to measure their statistical performance.
Mode recovery in neural autoregressive sequence modeling
We propose to study these phenomena by investigating how the modes, or local maxima, of a distribution are maintained throughout the full learning chain of the ground-truth, empirical, learned and decoding-induced distributions, via the newly proposed mode recovery cost.
NaturalProofs: Mathematical Theorem Proving in Natural Language
Understanding and creating mathematics using natural mathematical language - the mixture of symbolic and natural language used by humans - is a challenging and important problem for driving progress in machine learning.
MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers
As major progress is made in open-ended text generation, measuring how close machine-generated text is to human language remains a critical open problem.
MLE-guided parameter search for task loss minimization in neural sequence modeling
Typical approaches to directly optimizing the task loss such as policy gradient and minimum risk training are based around sampling in the sequence space to obtain candidate update directions that are scored based on the loss of a single sequence.
Consistency of a Recurrent Language Model With Respect to Incomplete Decoding
Despite strong performance on a variety of tasks, neural sequence models trained with maximum likelihood have been shown to exhibit issues such as length bias and degenerate repetition.
Don't Say That! Making Inconsistent Dialogue Unlikely with Unlikelihood Training
Generative dialogue models currently suffer from a number of problems which standard maximum likelihood training does not address.
Neural Text Generation with Unlikelihood Training
Neural text generation is a key tool in natural language applications, but it is well known there are major problems at its core.
A Generalized Framework of Sequence Generation with Application to Undirected Sequence Models
We investigate this problem by proposing a generalized model of sequence generation that unifies decoding in directed and undirected models.
Sequential Graph Dependency Parser
We propose a method for non-projective dependency parsing by incrementally predicting a set of edges.
Non-Monotonic Sequential Text Generation
Standard sequential generation methods assume a pre-specified generation order, such as text generation methods which generate words from left to right.
Loss Functions for Multiset Prediction
In this paper, we propose a novel multiset loss function by viewing this problem from the perspective of sequential decision making.
Saliency-based Sequential Image Attention with Multiset Prediction
Humans process visual scenes selectively and sequentially using attention.
