Search Results for author:
Found 29 papers, 6 papers with code
LibEvolutionEval: A Benchmark and Study for Version-Specific Code Generation
Recent advancements in code completion models have primarily focused on local file contexts.
Approximately Aligned Decoding
It is common to reject undesired outputs of Large Language Models (LLMs); however, current methods to do so require an excessive amount of computation, or severely distort the distribution of outputs.
LeDex: Training LLMs to Better Self-Debug and Explain Code
We thus propose an automated pipeline to collect a high-quality dataset for code explanation and refinement by generating a number of explanations and refinement trajectories from the LLM itself or a larger teacher model and filtering via execution verification.
BASS: Batched Attention-optimized Speculative Sampling
Speculative decoding has emerged as a powerful method to improve latency and throughput in hosting large language models.
CodeFort: Robust Training for Code Generation Models
Code generation models are not robust to small perturbations, which often lead to incorrect generations and significantly degrade the performance of these models.
Repoformer: Selective Retrieval for Repository-Level Code Completion
Recent advances in retrieval-augmented generation (RAG) have initiated a new era in repository-level code completion.
Code Representation Learning At Scale
Recent studies have shown that code language models at scale demonstrate significant performance gains on downstream tasks, i. e., code generation.
Code-Aware Prompting: A study of Coverage Guided Test Generation in Regression Setting using LLM
Recent works using large language models (LLMs) for test generation have focused on improving generation quality through optimizing the test generation context and correcting errors in model outputs, but use fixed prompting strategies that prompt the model to generate tests without additional guidance.
Lightweight reranking for language model generations
We show strong improvements for selecting the best k generations for code generation tasks as well as robust improvements for the best generation for the tasks of autoformalization, summarization, and translation.
Exploring Continual Learning for Code Generation Models
Large-scale code generation models such as Codex and CodeT5 have achieved impressive performance.
Efficient Shapley Values Estimation by Amortization for Text Classification
In practice, Shapley Values are often estimated with a small number of stochastic model evaluations.
STREET: A Multi-Task Structured Reasoning and Explanation Benchmark
We introduce STREET, a unified multi-task and multi-domain natural language reasoning and explanation benchmark.
SWING: Balancing Coverage and Faithfulness for Dialogue Summarization
Missing information is a common issue of dialogue summarization where some information in the reference summaries is not covered in the generated summaries.
ContraCLM: Contrastive Learning For Causal Language Model
Specifically, we attain $44\%$ relative improvement on the Semantic Textual Similarity tasks and $34\%$ on Code-to-Code Search tasks.
Learning Dialogue Representations from Consecutive Utterances
In this paper, we introduce Dialogue Sentence Embedding (DSE), a self-supervised contrastive learning method that learns effective dialogue representations suitable for a wide range of dialogue tasks.
Entailment Tree Explanations via Iterative Retrieval-Generation Reasoner
Our model is able to explain a given hypothesis by systematically generating a step-by-step explanation from textual premises.
Debiasing Neural Retrieval via In-batch Balancing Regularization
People frequently interact with information retrieval (IR) systems, however, IR models exhibit biases and discrimination towards various demographics.
Robust Information Retrieval for False Claims with Distracting Entities In Fact Extraction and Verification
A BERT-based retrieval model made more mistakes in retrieving refuting evidence for false claims than supporting evidence for true claims.
Contrastive Document Representation Learning with Graph Attention Networks
In this work, we propose to use a graph attention network on top of the available pretrained Transformers model to learn document embeddings.
Virtual Augmentation Supported Contrastive Learning of Sentence Representations
We then define an instance discrimination task regarding this neighborhood and generate the virtual augmentation in an adversarial training manner.
Contrastive Fine-tuning Improves Robustness for Neural Rankers
The performance of state-of-the-art neural rankers can deteriorate substantially when exposed to noisy inputs or applied to a new domain.
Uncertainty-Based Adaptive Learning for Reading Comprehension
Recent years have witnessed a surge of successful applications of machine reading comprehension.
Beyond [CLS] through Ranking by Generation
Generative models for Information Retrieval, where ranking of documents is viewed as the task of generating a query from a document's language model, were very successful in various IR tasks in the past.
AWS CORD-19 Search: A Neural Search Engine for COVID-19 Literature
Coronavirus disease (COVID-19) has been declared as a pandemic by WHO with thousands of cases being reported each day.
Domain Adaptation with BERT-based Domain Classification and Data Selection
The performance of deep neural models can deteriorate substantially when there is a domain shift between training and test data.
Universal Text Representation from BERT: An Empirical Study
We present a systematic investigation of layer-wise BERT activations for general-purpose text representations to understand what linguistic information they capture and how transferable they are across different tasks.
Multi-passage BERT: A Globally Normalized BERT Model for Open-domain Question Answering
To tackle this issue, we propose a multi-passage BERT model to globally normalize answer scores across all passages of the same question, and this change enables our QA model find better answers by utilizing more passages.
Ranked #3 on
Open-Domain Question Answering
on SearchQA
Passage Ranking with Weak Supervision
In this paper, we propose a \textit{weak supervision} framework for neural ranking tasks based on the data programming paradigm \citep{Ratner2016}, which enables us to leverage multiple weak supervision signals from different sources.
Hierarchical Clustering with Prior Knowledge
Being greedy in the algorithmic sense, a hierarchical clustering partitions data at every step solely based on a similarity / dissimilarity measure.
