Related papers: Example-Free Learning of Regular Languages with Pr…

Continual Learning aims to learn a single model on a sequence of tasks without having access to data from previous tasks. The biggest challenge in the domain still remains catastrophic forgetting: a loss in performance on seen classes of…

Reinforcement learning (RL) has emerged as a powerful framework for improving the reasoning capabilities of large language models (LLMs). However, most existing RL approaches rely on sparse outcome rewards, which fail to credit correct…

Trained on the large corpus, pre-trained language models (PLMs) can capture different levels of concepts in context and hence generate universal language representations. They can benefit multiple downstream natural language processing…

Domain-specific contextualized language models have demonstrated substantial effectiveness gains for domain-specific downstream tasks, like similarity matching, entity recognition or information retrieval. However successfully applying such…

In recent years some researchers have explored the use of reinforcement learning (RL) algorithms as key components in the solution of various natural language processing tasks. For instance, some of these algorithms leveraging deep neural…

Large Language Models (LLMs) have significantly advanced the field of information retrieval, particularly for reranking. Listwise LLM rerankers have showcased superior performance and generalizability compared to existing supervised…

We address the problem of reward hacking, where maximising a proxy reward does not necessarily increase the true reward. This is a key concern for Large Language Models (LLMs), as they are often fine-tuned on human preferences that may not…

Pretrained Language Models (LMs) memorize a vast amount of knowledge during initial pretraining, including information that may violate the privacy of personal lives and identities. Previous work addressing privacy issues for language…

With the release of new large language models (LLMs) like Llama and Mistral, zero-shot cross-lingual transfer has become increasingly feasible due to their multilingual pretraining and strong generalization capabilities. However, adapting…

Large pre-trained language models (PLMs) have demonstrated strong performance on natural language understanding (NLU) tasks through fine-tuning. However, fine-tuned models still suffer from overconfident predictions, especially in…

Speaker recognition models face challenges in multi-lingual settings due to the entanglement of linguistic information within speaker embeddings. The overlap between vocal traits such as accent, vocal anatomy, and a language's phonetic…

Language models often pre-train on large unsupervised text corpora, then fine-tune on additional task-specific data. However, typical fine-tuning schemes do not prioritize the examples that they tune on. We show that, if you can prioritize…

In order for large language model (LLM)-based assistants to effectively adapt to evolving information needs, it must be possible to update their factual knowledge through continued training on new data. The standard recipe for doing so…

As language models (LMs) deliver increasing performance on a range of NLP tasks, probing classifiers have become an indispensable technique in the effort to better understand their inner workings. A typical setup involves (1) defining an…

Modern large-scale Pre-trained Language Models (PLMs) have achieved tremendous success on a wide range of downstream tasks. However, most of the LM pre-training objectives only focus on text reconstruction, but have not sought to learn…

In recent years, Large Language Models (LLMs) have made significant strides towards Artificial General Intelligence. However, training these models from scratch requires substantial computational resources and vast amounts of text data. In…

The success of speech assistants requires precise recognition of a number of entities on particular contexts. A common solution is to train a class-based n-gram language model and then expand the classes into specific words or phrases.…

Making an informed choice of pre-trained language model (LM) is critical for performance, yet environmentally costly, and as such widely underexplored. The field of Computer Vision has begun to tackle encoder ranking, with promising forays…

Environments with procedurally generated content serve as important benchmarks for testing systematic generalization in deep reinforcement learning. In this setting, each level is an algorithmically created environment instance with a…

Lip reading, also known as visual speech recognition, aims to recognize the speech content from videos by analyzing the lip dynamics. There have been several appealing progress in recent years, benefiting much from the rapidly developed…