Related papers: REM-Net: Recursive Erasure Memory Network for Comm…

Commonsense question answering aims to answer questions which require background knowledge that is not explicitly expressed in the question. The key challenge is how to obtain evidence from external knowledge and make predictions based on…

Cross-modal retrieval relies on well-matched large-scale datasets that are laborious in practice. Recently, to alleviate expensive data collection, co-occurring pairs from the Internet are automatically harvested for training. However, it…

When answering a question, people often draw upon their rich world knowledge in addition to the particular context. Recent work has focused primarily on answering questions given some relevant document or context, and required very little…

Machine unlearning is studied for a multitude of tasks, but specialization of unlearning methods to particular tasks has made their systematic comparison challenging. To address this issue, we propose a conceptual space to characterize…

Hypothesis testing is an important cognitive process that supports human reasoning. In this paper, we introduce a computational hypothesis testing approach based on memory augmented neural networks. Our approach involves a hypothesis…

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…

Retrieval-Augmented Generation (RAG) enables large language models (LLMs) to access broader knowledge sources, yet factual inconsistencies persist due to noise in retrieved documents-even with advanced retrieval methods. We demonstrate that…

Question answering (QA) using textual sources for purposes such as reading comprehension (RC) has attracted much attention. This study focuses on the task of explainable multi-hop QA, which requires the system to return the answer with…

Document-level relation extraction (Doc-RE) aims to extract relations between entities across multiple sentences. Therefore, Doc-RE requires more comprehensive reasoning abilities like humans, involving complex cross-sentence interactions…

Recurrent neural networks for session-based recommendation have attracted a lot of attention recently because of their promising performance. repeat consumption is a common phenomenon in many recommendation scenarios (e.g., e-commerce,…

Commonsense reasoning is a long-standing challenge for deep learning. For example, it is difficult to use neural networks to tackle the Winograd Schema dataset (Levesque et al., 2011). In this paper, we present a simple method for…

Extreme learning machine (ELM) as an emerging branch of shallow networks has shown its excellent generalization and fast learning speed. However, for blended data, the robustness of ELM is weak because its weights and biases of hidden nodes…

Referring Expression Comprehension (REC) is a foundational cross-modal task that evaluates the interplay of language understanding, image comprehension, and language-to-image grounding. It serves as an essential testing ground for…

Understanding learning materials (e.g. test questions) is a crucial issue in online learning systems, which can promote many applications in education domain. Unfortunately, many supervised approaches suffer from the problem of scarce human…

To tackle long-context reasoning tasks without the quadratic complexity of standard attention mechanisms, approaches based on agent memory have emerged, which typically maintain a dynamically updated memory when linearly processing document…

We propose a new paradigm to help Large Language Models (LLMs) generate more accurate factual knowledge without retrieving from an external corpus, called RECITation-augmented gEneration (RECITE). Different from retrieval-augmented language…

Retrieval-Augmented Generation (RAG) enhances the performance of Large Language Models (LLMs) by incorporating external knowledge. However, LLMs still encounter challenges in effectively utilizing the knowledge from retrieved documents,…

Evidence plays a crucial role in automated fact-checking. When verifying real-world claims, existing fact-checking systems either assume the evidence sentences are given or use the search snippets returned by the search engine. Such methods…

Existing conversational systems tend to generate generic responses. Recently, Background Based Conversations (BBCs) have been introduced to address this issue. Here, the generated responses are grounded in some background information. The…

Large Language Models (LLMs) have shown strong capabilities in document re-ranking, a key component in modern Information Retrieval (IR) systems. However, existing LLM-based approaches face notable limitations, including ranking…