Related papers: Programming Language Agnostic Mining of Code and L…

The performance of large language models (LLMs) is closely linked to their underlying size, leading to ever-growing networks and hence slower inference. Speculative decoding has been proposed as a technique to accelerate autoregressive…

We introduce aligned probing, a novel interpretability framework that aligns the behavior of language models (LMs), based on their outputs, and their internal representations (internals). Using this framework, we examine over 20 OLMo,…

Large language models (LLMs) have revolutionized Text-to-SQL generation, allowing users to query structured data using natural language with growing ease. Yet, real-world deployment remains challenging, especially in complex or unseen…

The safe and effective deployment of Large Language Models (LLMs) involves a critical step called alignment, which ensures that the model's responses are in accordance with human preferences. Prevalent alignment techniques, such as DPO, PPO…

As LLMs have become increasingly popular, they have been used in almost every field. But as the application for LLMs expands from generic fields to narrow, focused science domains, there exists an ever-increasing gap in ways to evaluate…

Progress in cross-lingual modeling depends on challenging, realistic, and diverse evaluation sets. We introduce Multilingual Knowledge Questions and Answers (MKQA), an open-domain question answering evaluation set comprising 10k…

The Knowledge Base Question Answering (KBQA) task aims to answer natural language questions based on a given knowledge base. Recently, Large Language Models (LLMs) have shown strong capabilities in language understanding and can be used to…

Computational notebooks, such as Jupyter notebooks, are interactive computing environments that are ubiquitous among data scientists to perform data wrangling and analytic tasks. To measure the performance of AI pair programmers that…

The rapid evolution of Natural Language Processing (NLP) has favoured major languages such as English, leaving a significant gap for many others due to limited resources. This is especially evident in the context of data annotation, a task…

Large Language Models (LLMs) are increasingly adopted as conversational assistants in genomics, where they are mainly used to reason over biological knowledge, annotations, and analysis outputs through natural language interfaces. However,…

Knowledge Graph Question Answering (KGQA) systems are based on machine learning algorithms, requiring thousands of question-answer pairs as training examples or natural language processing pipelines that need module fine-tuning. In this…

Transformer-based pretrained language models (PLMs) offer unmatched performance across the majority of natural language understanding (NLU) tasks, including a body of question answering (QA) tasks. We hypothesize that improvements in QA…

Large Language Models (LLMs) have demonstrated remarkable performance across various disciplines and tasks. However, benchmarking their capabilities with multilingual spoken queries remains largely unexplored. In this study, we introduce…

The logic-based machine-understandable framework of the Semantic Web often challenges naive users when they try to query ontology-based knowledge bases. Existing research efforts have approached this problem by introducing Natural Language…

Existing question answering (QA) systems owe much of their success to large, high-quality training data. Such annotation efforts are costly, and the difficulty compounds in the cross-lingual setting. Therefore, prior cross-lingual QA work…

This paper looks at semi-supervised learning (SSL) for image-based text recognition. One of the most popular SSL approaches is pseudo-labeling (PL). PL approaches assign labels to unlabeled data before re-training the model with a…

Large language models (LLMs) have made significant strides in code generation, achieving impressive capabilities in synthesizing code snippets from natural language instructions. However, a critical challenge remains in ensuring LLMs…

Aspect-based sentiment analysis (ABSA) has made significant strides, yet challenges remain for low-resource languages due to the predominant focus on English. Current cross-lingual ABSA studies often centre on simpler tasks and rely heavily…

As scientific knowledge grows at an unprecedented pace, evaluation benchmarks must evolve to reflect new discoveries and ensure language models are tested on current, diverse literature. We propose a scalable, modular framework for…

Text detoxification, a variant of style transfer tasks, finds useful applications in online social media. This work presents a fine-tuning method that only uses non-parallel data to turn large language models (LLM) into a detoxification…