Related papers: Ask Question First for Enhancing Lifelong Language…

Existing fraud detection methods predominantly rely on transcribed text, suffering from ASR errors and missing crucial acoustic cues like vocal tone and environmental context. This limits their effectiveness against complex deceptive…

Information-seeking conversation systems are increasingly popular in real-world applications, especially for e-commerce companies. To retrieve appropriate responses for users, it is necessary to compute the matching degrees between…

Pseudo-relevance feedback (PRF) can enhance average retrieval effectiveness over a sufficiently large number of queries. However, PRF often introduces a drift into the original information need, thus hurting the retrieval effectiveness of…

Continual Learning in Visual Question Answering (VQACL) requires models to acquire new visual-linguistic skills (plasticity) while preserving previously learned knowledge (stability). The inherent multimodality of VQACL exacerbates this…

Recent studies show that the reasoning capabilities of Large Language Models (LLMs) can be improved by applying Reinforcement Learning (RL) to question-answering (QA) tasks in areas such as math and coding. With a long context length, LLMs…

Disfluencies is an under-studied topic in NLP, even though it is ubiquitous in human conversation. This is largely due to the lack of datasets containing disfluencies. In this paper, we present a new challenge question answering dataset,…

Existing approaches to lifelong language learning rely on plenty of labeled data for learning a new task, which is hard to obtain in most real scenarios. Considering that humans can continually learn new tasks from a handful of examples, we…

We present Attentive Reasoning Queries (ARQs), a novel structured reasoning approach that significantly improves instruction-following in Large Language Models through domain-specialized reasoning blueprints. While LLMs demonstrate…

Multi-hop question answering (QA) requires reasoning over multiple documents to answer a complex question and provide interpretable supporting evidence. However, providing supporting evidence is not enough to demonstrate that a model has…

Our goal is a teachable reasoning system for question-answering (QA), where a user can interact with faithful answer explanations, and correct its errors so that the system improves over time. Our approach is to augment a QA model with a…

Recent advances in Large Language Models (LLMs) and Reinforcement Learning (RL) have led to strong performance in open-domain question answering (QA). However, existing models still struggle with questions that admit multiple valid answers.…

Large language models (LLMs) have significantly improved their reasoning and decision-making capabilities, as seen in methods like ReAct. However, despite its effectiveness in tackling complex tasks, ReAct faces two main challenges: losing…

Long-form question answering (LFQA) aims at generating in-depth answers to end-user questions, providing relevant information beyond the direct answer. However, existing retrievers are typically optimized towards information that directly…

Lifelong learning aims to accumulate knowledge and alleviate catastrophic forgetting when learning tasks sequentially. However, existing lifelong language learning methods only focus on the supervised learning setting. Unlabeled data, which…

Large language models (LLMs) have shown remarkable capabilities in various natural language processing tasks, yet they often struggle with maintaining factual accuracy, particularly in knowledge-intensive domains like healthcare. This study…

This paper explores the task of answer-aware questions generation. Based on the attention-based pointer generator model, we propose to incorporate an auxiliary task of language modeling to help question generation in a hierarchical…

Large Language Models (LLMs) have been showing promising results for various NLP-tasks without the explicit need to be trained for these tasks by using few-shot or zero-shot prompting techniques. A common NLP-task is question-answering…

We consider the problem of conversational question answering over a large-scale knowledge base. To handle huge entity vocabulary of a large-scale knowledge base, recent neural semantic parsing based approaches usually decompose the task…

Language Models (LMs) have revolutionized natural language processing, enabling high-quality text generation through prompting and in-context learning. However, models often struggle with long-context summarization due to positional biases,…

Query rewriting (QR) is an increasingly important technique to reduce customer friction caused by errors in a spoken language understanding pipeline, where the errors originate from various sources such as speech recognition errors,…