Related papers: Retrieval Enhanced Model for Commonsense Generatio…

The remarkable ability of Large Language Models (LLMs) to understand and follow instructions has sometimes been limited by their in-context learning (ICL) performance in low-resource languages. To address this, we introduce a novel approach…

Recent neural sequence-to-sequence models with a copy mechanism have achieved remarkable progress in various text generation tasks. These models addressed out-of-vocabulary problems and facilitated the generation of rare words. However, the…

Enthymemes are defined as arguments where a premise or conclusion is left implicit. We tackle the task of generating the implicit premise in an enthymeme, which requires not only an understanding of the stated conclusion and premise but…

Many conversation datasets have been constructed in the recent years using crowdsourcing. However, the data collection process can be time consuming and presents many challenges to ensure data quality. Since language generation has improved…

Establishing retrieval-based dialogue systems that can select appropriate responses from the pre-built index has gained increasing attention from researchers. For this task, the adoption of pre-trained language models (such as BERT) has led…

Commonsense reasoning has long been considered as one of the holy grails of artificial intelligence. Most of the recent progress in the field has been achieved by novel machine learning algorithms for natural language processing. However,…

Large language models have demonstrated impressive reasoning capabilities but are inherently limited by their knowledge reservoir. Retrieval-augmented reasoning mitigates this limitation by allowing LLMs to query external resources, but…

Current state-of-the-art large language models are effective in generating high-quality text and encapsulating a broad spectrum of world knowledge. These models, however, often hallucinate and lack locally relevant factual data.…

Beyond generating long and topic-coherent paragraphs in traditional captioning tasks, the medical image report composition task poses more task-oriented challenges by requiring both the highly-accurate medical term diagnosis and multiple…

Effective cross-lingual dense retrieval methods that rely on multilingual pre-trained language models (PLMs) need to be trained to encompass both the relevance matching task and the cross-language alignment task. However, cross-lingual data…

Research on conversational search has so far mostly focused on query rewriting and multi-stage passage retrieval. However, synthesizing the top retrieved passages into a complete, relevant, and concise response is still an open challenge.…

Retrieval-augmented language models (LMs) have received much attention recently. However, typically the retriever is not trained jointly as a native component of the LM, but added post-hoc to an already-pretrained LM, which limits the…

Open domain response generation has achieved remarkable progress in recent years, but sometimes yields short and uninformative responses. We propose a new paradigm for response generation, that is response generation by editing, which…

Generative retrieval is an emerging approach in information retrieval that generates identifiers (IDs) of target data based on a query, providing an efficient alternative to traditional embedding-based retrieval methods. However, existing…

Large language models (LLM) often hallucinate, and while adding citations is a common solution, it is frequently insufficient for accountability as users struggle to verify how a cited source supports a generated claim. Existing methods are…

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…

In retrieval-augmented generation (RAG) question answering systems, generating citations for large language model (LLM) outputs enhances verifiability and helps users identify potential hallucinations. However, we observe two problems in…

Deep neural networks have achieved state-of-the-art results in various vision and/or language tasks. Despite the use of large training datasets, most models are trained by iterating over single input-output pairs, discarding the remaining…

Language technologies that accurately model the dynamics of events must perform commonsense reasoning. Existing work evaluating commonsense reasoning focuses on making inferences about common, everyday situations. To instead investigate the…

Knowledge-intensive language tasks (KILT) usually require a large body of information to provide correct answers. A popular paradigm to solve this problem is to combine a search system with a machine reader, where the former retrieves…