Related papers: Exploring Hybrid Question Answering via Program-ba…
Automatic prompt optimization has recently emerged as a strategy for improving the quality of prompts used in Large Language Models (LLMs), with the goal of generating more accurate and useful responses. However, most prior work focuses on…
When answering complex questions, people can seamlessly combine information from visual, textual and tabular sources. While interest in models that reason over multiple pieces of evidence has surged in recent years, there has been…
We present a new multimodal question answering challenge, ManyModalQA, in which an agent must answer a question by considering three distinct modalities: text, images, and tables. We collect our data by scraping Wikipedia and then utilize…
Question answering is one of the primary challenges of natural language understanding. In realizing such a system, providing complex long answers to questions is a challenging task as opposed to factoid answering as the former needs context…
Continual learning requires machine learning models to continuously acquire new knowledge in dynamic environments while avoiding the forgetting of previous knowledge. Prompt-based continual learning methods effectively address the issue of…
Reading comprehension QA tasks have seen a recent surge in popularity, yet most works have focused on fact-finding extractive QA. We instead focus on a more challenging multi-hop generative task (NarrativeQA), which requires the model to…
Unsupervised question answering is an attractive task due to its independence on labeled data. Previous works usually make use of heuristic rules as well as pre-trained models to construct data and train QA models. However, most of these…
Programs, consisting of semantic and structural information, play an important role in the communication between humans and agents. Towards learning general program executors to unify perception, reasoning, and decision making, we formulate…
Existing question answering (QA) datasets fail to train QA systems to perform complex reasoning and provide explanations for answers. We introduce HotpotQA, a new dataset with 113k Wikipedia-based question-answer pairs with four key…
We propose a novel open-domain question answering (ODQA) framework for answering single/multi-hop questions across heterogeneous knowledge sources. The key novelty of our method is the introduction of the intermediary modules into the…
Asking questions from natural language text has attracted increasing attention recently, and several schemes have been proposed with promising results by asking the right question words and copy relevant words from the input to the…
This paper surveys and organizes research works in a new paradigm in natural language processing, which we dub "prompt-based learning". Unlike traditional supervised learning, which trains a model to take in an input x and predict an output…
Prompting is a mainstream paradigm for adapting large language models to specific natural language processing tasks without modifying internal parameters. Therefore, detailed supplementary knowledge needs to be integrated into external…
Numerical reasoning over table-and-text hybrid passages, such as financial reports, poses significant challenges and has numerous potential applications. Noise and irrelevant variables in the model input have been a hindrance to its…
A multi-hop question answering (QA) dataset aims to test reasoning and inference skills by requiring a model to read multiple paragraphs to answer a given question. However, current datasets do not provide a complete explanation for the…
It remains an open question whether incorporating external knowledge benefits commonsense reasoning while maintaining the flexibility of pretrained sequence models. To investigate this question, we develop generated knowledge prompting,…
Graph Retrieval-Augmented Generation (GraphRAG) has emerged as a promising paradigm that organizes external knowledge into structured graphs of entities and relations, enabling large language models (LLMs) to perform complex reasoning…
Formally specifying, let alone verifying, properties of systems involving multiple programming languages is inherently challenging. We introduce Heterogeneous Dynamic Logic (HDL), a framework for combining reasoning principles from distinct…
Pragmatic reasoning helps interlocutors infer intended meaning from ambiguous or underspecified messages by considering shared context and counterfactual alternatives. Similar challenges arise in natural language-to-code generation, where…
Multi-hop Question Answering (QA) is a challenging task since it requires an accurate aggregation of information from multiple context paragraphs and a thorough understanding of the underlying reasoning chains. Recent work in multi-hop QA…