Related papers: Happy-GLL: modular, reusable and complete top-down…

Nearly all general-purpose neural semantic parsers generate logical forms in a strictly top-down autoregressive fashion. Though such systems have achieved impressive results across a variety of datasets and domains, recent works have called…

Large language models are increasingly capable of generating fluent-appearing text with relatively little task-specific supervision. But can these models accurately explain classification decisions? We consider the task of generating…

Retrieval-augmented large language models (LLMs) leverage relevant content retrieved by information retrieval systems to generate correct responses, aiming to alleviate the hallucination problem. However, existing retriever-responder…

Large language models (LLMs) are incredibly powerful at comprehending and generating data in the form of text, but are brittle and error-prone. There has been an advent of toolkits and recipes centered around so-called prompt…

Syntax-directed translation tools require the specification of a language by means of a formal grammar. This grammar must conform to the specific requirements of the parser generator to be used. This grammar is then annotated with semantic…

Cross-domain natural language generation (NLG) is still a difficult task within spoken dialogue modelling. Given a semantic representation provided by the dialogue manager, the language generator should generate sentences that convey…

In recent years, a significant number of high-quality pretrained models have emerged, greatly impacting Natural Language Understanding (NLU), Natural Language Generation (NLG), and Text Representation tasks. Traditionally, these models are…

Over the past few years, improving LLM code generation capabilities has been a key focus in NLP research. Despite Bengali having 242 million native speakers worldwide, it receives little attention when it comes to training LLMs. More…

Large language models (LLMs) have demonstrated impressive capabilities in natural language generation. However, their output quality can be inconsistent, posing challenges for generating natural language from logical forms (LFs). This task…

Large Language Models (LLMs) have demonstrated strong reasoning abilities, making them suitable for complex tasks such as graph computation. Traditional reasoning steps paradigm for graph problems is hindered by unverifiable steps, limited…

In this work, we undertake the challenge of augmenting the existing generative capabilities of pre-trained text-only large language models (LLMs) with multi-modal generation capability while satisfying two core constraints: C1 preserving…

Large language models (LLMs) are often augmented with tools to solve complex tasks. By generating code snippets and executing them through task-specific Application Programming Interfaces (APIs), they can offload certain functions to…

Pre-trained language models have been successful in natural language generation (NLG) tasks. While various decoding methods have been employed, they often produce suboptimal results. We first present an empirical analysis of three NLG…

Large language models (LLMs) have achieved strong empirical performance in various fields, benefiting from their huge amount of parameters that store knowledge. However, LLMs still suffer from several key issues, such as hallucination…

The use of large language models (LLMs) as feature enhancers to optimize node representations, which are then used as inputs for graph neural networks (GNNs), has shown significant potential in graph representation learning. However, the…

Automated front-end engineering drastically reduces development cycles and minimizes manual coding overhead. While Generative AI has shown promise in translating designs to code, current solutions often produce monolithic scripts, failing…

LLMs have demonstrated commendable performance across diverse domains. Nevertheless, formulating high-quality prompts to assist them in their work poses a challenge for non-AI experts. Existing research in prompt engineering suggests…

High-Level Synthesis has introduced reconfigurable logic to a new world -- that of software development. The newest wave of HLS tools has been successful, and the future looks bright. But is HLS the end-all-be-all to FPGA acceleration? Is…

Large Language Models (LLMs) have shown remarkable prowess in text generation, yet producing long-form, factual documents grounded in extensive external knowledge bases remains a significant challenge. Existing "top-down" methods, which…

Code generation maps a program description to executable source code in a programming language. Existing approaches mainly rely on a recurrent neural network (RNN) as the decoder. However, we find that a program contains significantly more…