Publications [home]

Parallelizing Linear Transformers with the Delta Rule over Sequence Length

Reuse Your Rewards: Reward Model Transfer for Zero-Shot Cross-Lingual Alignment

Fast Matrix Multiplications for Lookup Table-Quantized LLMs

Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps

paper

code

Improving Dialogue Agents by Decomposing One Global Explicit Annotation with Local Implicit Multimodal Feedback

paper

MDCR: A Dataset for Multi-Document Conditional Reasoning

paper

code

VizAbility: Enhancing Chart Accessibility with LLM-based Conversational Interaction

paper

LLM economicus? Mapping the Behavioral Biases of LLMs via Utility Theory

paper

Towards Verifiable Text Generation with Symbolic References

paper

code

Learning to Decode Collaboratively with Multiple Language Models

paper

code

What Do Language Models Hear? Probing for Auditory Representations in Language Models

paper

Can You Learn Semantics Through Next-Word Prediction? The Case of Entailment

paper

CHAMP: A Competition-level Dataset for Fine-Grained Analyses of LLMs' Mathematical Reasoning Capabilities

paper

code

Leveraging Large Language Models for Learning Complex Legal Concepts through Storytelling

paper

Gated Linear Attention Transformers with Hardware-Efficient Training

paper

slides

code

In-Context Language Learning: Architectures and Algorithms

paper

code

Data Engineering for Scaling Language Models to 128K Context

paper

code

Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks

paper

code

LangNav: Language as a Perceptual Representation for Navigation

paper

Natural Language Embedded Programs for Hybrid Language Symbolic Reasoning

paper

code

Paraphrase and Solve: Exploring and Exploiting the Impact of Surface Form on Mathematical Reasoning in Large Language Models

paper

code

LQ-LoRA: Low-rank Plus Quantized Matrix Decomposition for Efficient Language Model Finetuning

paper

code

Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement

paper

DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models

paper

code

Alignment via Mutual Information

paper

Explain-then-Translate: An Analysis on Improving Program Translation with Self-generated Explanations

paper

code

Simple Hardware-Efficient PCFGs with Independent Left and Right Productions

paper

code

SAIL: Search-Augmented Instruction Learning

paper

code

Audio-Visual Neural Syntax Acquisition

paper

Grammar Prompting for Domain-Specific Language Generation with Large Language Models

paper

slides

code

Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors

paper

code

Unsupervised Discontinuous Constituency Parsing with Mildly Context-Sensitive Grammars

paper

code

Deriving Language Models from Masked Language Models

paper

Entailment as Robust Self-Learner

paper

code

Learning to Grow Pretrained Models for Efficient Transformer Training

paper

code

Multitask Prompt Tuning Enables Parameter-efficient Transfer Learning

paper

code

Federated Learning as Variational Inference: A Scalable Expectation Propagation Approach

paper

code

Hierarchical Phrase-based Sequence-to-Sequence Learning

paper

slides

code

Probing for Incremental Parse States in Autoregressive Language Models

paper

Large Language Models are Few-Shot Clinical Information Extractors

paper

Co-training Improves Prompt-based Learning for Large Language Models

paper

slides

code

DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings

paper

code

Inducing and Using Alignments for Transition-based AMR Parsing

paper

VALHALLA: Visual Hallucination for Machine Translation

paper

code

Controlling the Focus of Pretrained Language Generation Models

paper

code

Sequence-to-Sequence Learning with Latent Neural Grammars

paper

slides

code

Kori: Interactive Synthesis of Text and Charts in Data Documents

paper

Developmental Stage Classification of Embryos Using Two-Stream Neural Network with Linear-Chain Conditional Random Field

paper

Syntactic Perturbations Reveal Representational Correlates of Hierarchical Phrase Structure in Pretrained Language Models

paper

Parameter-Efficient Transfer Learning with Diff Pruning

paper

slides

code

Sequence-Level Mixed Sample Data Augmentation

paper

code

Empirical Study of the Benefits of Overparameterization in Learning Latent Variable Models

paper

code

Emergence of Separable Manifolds in Deep Language Representations

paper

Amortized Bethe Free Energy Minimization for Learning MRFs

paper

code

Compound Probabilistic Context-Free Grammars for Grammar Induction

paper

slides

code

Unsupervised Recurrent Neural Network Grammars

paper

slides

code

Avoiding Latent Variable Collapse with Generative Skip Models

paper

code

A Tutorial on Deep Latent Variable Models of Natural Language

paper

slides

code

Latent Alignment and Variational Attention

paper

code

On the Flip Side: Identifying Counterexamples in Visual Question Answering

paper

code

Semi-Amortized Variational Autoencoders

paper

slides

code

Adversarially Regularized Autoencoders

paper

slides

code

Adapting Sequence Models for Sentence Correction

paper

Structured Attention Networks

paper

slides

code

OpenNMT: Open-Source Toolkit for Neural Machine Translation

paper

code

Sequence-Level Knowledge Distillation

paper

slides

Sentence-Level Grammatical Error Identification as Sequence-to-Sequence Correction

paper

Character-Aware Neural Language Models

paper

slides

code

Convolutional Neural Networks for Sentence Classification

paper

slides

code

Temporal Analysis of Language through Neural Language Models

paper

Credibility Adjusted Term Frequency: A Supervised Term Weighting Scheme for Sentiment Analysis and Text Classification

paper