6 papers · 1 filter
Does Out-of-Sight Equal Out-of-Mind in CoT Monitorability?
Pedro Ferreira, Wilker Aziz, Ivan Titov
Chain-of-thought (CoT) reasoning offers a window into the decision-making of large language models (LLMs), which can be monitored for target behaviors by reading the reasoning trac…
Clarify, Abstain or Answer? Strategising in Conversation with Belief-Augmented Generation
Joris Baan, Wilker Aziz, Barbara Plank +1
Large language models (LLMs) define a distribution over text, which can be viewed as a probabilistic representation of uncertainty: sampling K responses yields a belief state - res…
Truthful or Fabricated? Using Causal Attribution to Mitigate Reward Hacking in Explanations
Pedro Ferreira, Wilker Aziz, Ivan Titov
Chain-of-thought explanations are widely used to inspect the decision process of large language models (LLMs) and to evaluate the trustworthiness of model outputs, making them impo…
Explanation Regularisation through the Lens of Attributions
Pedro Ferreira, Ivan Titov, Wilker Aziz
Explanation regularisation (ER) has been introduced as a way to guide text classifiers to form their predictions relying on input tokens that humans consider plausible. This is ach…
Interpretable Neural Predictions with Differentiable Binary Variables
Jasmijn Bastings, Wilker Aziz, Ivan Titov
The success of neural networks comes hand in hand with a desire for more interpretability. We focus on text classifiers and make them more interpretable by having them provide a ju…
Question Answering by Reasoning Across Documents with Graph Convolutional Networks
Nicola De Cao, Wilker Aziz, Ivan Titov
Most research in reading comprehension has focused on answering questions based on individual documents or even single paragraphs. We introduce a neural model which integrates and…