Related papers: ZeroSCROLLS: A Zero-Shot Benchmark for Long Text U…

We equip a smaller Language Model to generalise to answering challenging compositional questions that have not been seen in training. To do so we propose a combination of multitask supervised pretraining on up to 93 tasks designed to…

Large language models (LLM) have been successful in several natural language understanding tasks and could be relevant for natural language processing (NLP)-based mental health application research. In this work, we report the performance…

There is growing interest in systems that generate captions for scientific figures. However, assessing these systems output poses a significant challenge. Human evaluation requires academic expertise and is costly, while automatic…

Massively multilingual language models have displayed strong performance in zero-shot (ZS-XLT) and few-shot (FS-XLT) cross-lingual transfer setups, where models fine-tuned on task data in a source language are transferred without any or…

Very large language models (LLMs) perform extremely well on a spectrum of NLP tasks in a zero-shot setting. However, little is known about their performance on human-level NLP problems which rely on understanding psychological concepts,…

Large language models have recently reached near-parity with classical planners on well-known planning domains, yet this competence relies on world-knowledge exploitation rather than genuine symbolic reasoning. Goal recognition is a…

Recent studies have demonstrated promising potential of ChatGPT for various text annotation and classification tasks. However, ChatGPT is non-deterministic which means that, as with human coders, identical input can lead to different…

Large language models (LLMs) have demonstrated remarkable success in NLP tasks. However, there is a paucity of studies that attempt to evaluate their performances on social media-based health-related natural language processing tasks, which…

We present ACCORD, a framework and benchmark suite for disentangling the commonsense grounding and reasoning abilities of large language models (LLMs) through controlled, multi-hop counterfactuals. ACCORD introduces formal elements to…

While conversational semantic role labeling (CSRL) has shown its usefulness on Chinese conversational tasks, it is still under-explored in non-Chinese languages due to the lack of multilingual CSRL annotations for the parser training. To…

Improving multilingual language models capabilities in low-resource languages is generally difficult due to the scarcity of large-scale data in those languages. In this paper, we relax the reliance on texts in low-resource languages by…

Recent advances in training multilingual language models on large datasets seem to have shown promising results in knowledge transfer across languages and achieve high performance on downstream tasks. However, we question to what extent the…

We present an approach to build Large Language Model (LLM) based slot-filling system to perform Dialogue State Tracking in conversational assistants serving across a wide variety of industry-grade applications. Key requirements of this…

This work proposes a challenging yet more realistic setting for zero-shot cross-task generalization: zero-shot instruction following, presuming the existence of a paragraph-style task definition while no demonstrations exist. To better…

Large-scale generative language models such as GPT-3 are competitive few-shot learners. While these models are known to be able to jointly represent many different languages, their training data is dominated by English, potentially limiting…

Conventional approaches to text classification typically assume the existence of a fixed set of predefined labels to which a given text can be classified. However, in real-world applications, there exists an infinite label space for…

Zero-shot medical image classification is a critical process in real-world scenarios where we have limited access to all possible diseases or large-scale annotated data. It involves computing similarity scores between a query medical image…

Prompt tuning in natural language processing (NLP) has become an increasingly popular method for adapting large language models to specific tasks. However, the transferability of these prompts, especially continuous prompts, between…

In task-oriented conversational AI evaluation, unsupervised methods poorly correlate with human judgments, and supervised approaches lack generalization. Recent advances in large language models (LLMs) show robust zeroshot and few-shot…

We present a new approach to perform zero-shot cross-modal transfer between speech and text for translation tasks. Multilingual speech and text are encoded in a joint fixed-size representation space. Then, we compare different approaches to…