Related papers: Reading StackOverflow Encourages Cheating: Adding …
Large Language Models (LLMs) may hallucinate and generate fake information, despite pre-training on factual data. Inspired by the journalistic device of "according to sources", we propose according-to prompting: directing LLMs to ground…
Context: Stack Overflow is a popular community question and answer portal used by practitioners to solve problems during software development. Developers can focus their attention on answers that have been accepted or where members have…
Most Visual Question Answering (VQA) models suffer from the language prior problem, which is caused by inherent data biases. Specifically, VQA models tend to answer questions (e.g., what color is the banana?) based on the high-frequency…
Closed-book question answering (QA) requires a model to directly answer an open-domain question without access to any external knowledge. Prior work on closed-book QA either directly finetunes or prompts a pretrained language model (LM) to…
We study learning from user feedback for extractive question answering by simulating feedback using supervised data. We cast the problem as contextual bandit learning, and analyze the characteristics of several learning scenarios with focus…
Fine-tuning BERT-based models is resource-intensive in memory, computation, and time. While many prior works aim to improve inference efficiency via compression techniques, e.g., pruning, these works do not explicitly address the…
For tasks like code synthesis from natural language, code retrieval, and code summarization, data-driven models have shown great promise. However, creating these models require parallel data between natural language (NL) and code with…
React is a popular JavaScript framework in modern web application development. Due to its high performance and efficiency, many developers use this framework. Although React library offers many advantages, it is not without its challenges.…
In this paper we explore the parameter efficiency of BERT arXiv:1810.04805 on version 2.0 of the Stanford Question Answering dataset (SQuAD2.0). We evaluate the parameter efficiency of BERT while freezing a varying number of final…
Document-based question answering (QA) increasingly includes abstract questions that require synthesizing scattered information from long documents or across multiple documents into coherent answers. However, this setting is still poorly…
Reinforcement learning (RL) agents improve through trial-and-error, but when reward is sparse and the agent cannot discover successful action sequences, learning stagnates. This has been a notable problem in training deep RL agents to…
Compiler error messages serve as an initial resource for programmers dealing with compilation errors. However, previous studies indicate that they often lack sufficient targeted information to resolve code issues. Consequently, programmers…
Community Question Answering (CQA) becomes increasingly prevalent in recent years. However, there are a large number of answers, which is difficult for users to select the relevant answers. Therefore, answer selection is a very significant…
While hallucinations of large language models could been alleviated through retrieval-augmented generation and citation generation, how the model utilizes internal knowledge is still opaque, and the trustworthiness of its generated answers…
One of the first pre-processing steps for constructing web-scale LLM pretraining datasets involves extracting text from HTML. Despite the immense diversity of web content, existing open-source datasets predominantly apply a single fixed…
In order to facilitate natural language understanding, the key is to engage commonsense or background knowledge. However, how to engage commonsense effectively in question answering systems is still under exploration in both research…
Pretrained language models, such as BERT and RoBERTa, have shown large improvements in the commonsense reasoning benchmark COPA. However, recent work found that many improvements in benchmarks of natural language understanding are not due…
We introduce a new task of rephrasing for a more natural virtual assistant. Currently, virtual assistants work in the paradigm of intent slot tagging and the slot values are directly passed as-is to the execution engine. However, this setup…
On Stack Overflow, developers can not only browse question posts to solve their programming problems but also gain expertise from the question posts to help improve their programming skills. Therefore, improving the quality of question…
Detecting structural similarity between queries is essential for selecting examples in in-context learning models. However, assessing structural similarity based solely on the natural language expressions of queries, without considering SQL…