9 citations · 17 across the 16 of their papers we have counts for
16 papers
Counterfactual Tests for Measuring Chain-of-Thought Faithfulness in Visual Language Models
Bayar Menzat, Maximilian Süss, Ruizhi Wang +3
Chain-of-thought (CoT) may often look plausible, yet it may not faithfully reflect the model's decision-making process. While methods for measuring the faithfulness of CoTs for tex…
Training Large Language Models for Self-Explanation Faithfulness
Yeoktatt Cheah, María Pérez-Ortiz, Noah Y. Siegel +1
We propose a Reinforcement Learning (RL) method to directly optimize the faithfulness of self-explanations - the extent to which a model's generated reasoning accurately reflects i…
Biases in the Blind Spot: Detecting What LLMs Fail to Mention
Iván Arcuschin, David Chanin, Adrià Garriga-Alonso +1
Large Language Models (LLMs) often provide chain-of-thought (CoT) reasoning traces that appear plausible, but may hide internal biases. We call these unverbalized biases. Monitorin…
Verbosity Tradeoffs and the Impact of Scale on the Faithfulness of LLM Self-Explanations
Noah Y. Siegel, Nicolas Heess, Maria Perez-Ortiz +1
When asked to explain their decisions, LLMs can often give explanations which sound plausible to humans. But are these explanations faithful, i.e. do they convey the factors actual…
AnnoCaseLaw: Legal Annotation Benchmark of Civil Negligence
Magnus Sesodia, Rilton Franzone, Alina Petrova +7
Language models offer a way to scale costly, labour-intensive expert annotation, but their ability to reproduce expert judgements remains uncertain. This is particularly challengin…
Fool Me Once? Contrasting Textual and Visual Explanations in a Clinical Decision-Support Setting
Maxime Kayser, Bayar Menzat, Cornelius Emde +7
The growing capabilities of AI models are leading to their wider use, including in safety-critical domains. Explainable AI (XAI) aims to make these models safer to use by making th…
iLLuMinaTE: An LLM-XAI Framework Leveraging Social Science Explanation Theories Towards Actionable Student Performance Feedback
Vinitra Swamy, Davide Romano, Bhargav Srinivasa Desikan +2
Recent advances in eXplainable AI (XAI) for education have highlighted a critical challenge: ensuring that explanations for state-of-the-art AI models are understandable for non-te…
The Probabilities Also Matter: A More Faithful Metric for Faithfulness of Free-Text Explanations in Large Language Models
Noah Y. Siegel, Oana-Maria Camburu, Nicolas Heess +1
In order to oversee advanced AI systems, it is important to understand their underlying decision-making process. When prompted, large language models (LLMs) can provide natural lan…
Identifying Linear Relational Concepts in Large Language Models
David Chanin, Anthony Hunter, Oana-Maria Camburu
Transformer language models (LMs) have been shown to represent concepts as directions in the latent space of hidden activations. However, for any human-interpretable concept, how c…
Faithfulness Tests for Natural Language Explanations
Pepa Atanasova, Oana-Maria Camburu, Christina Lioma +3
Explanations of neural models aim to reveal a model's decision-making process for its predictions. However, recent work shows that current methods giving explanations such as salie…
KNOW How to Make Up Your Mind! Adversarially Detecting and Alleviating Inconsistencies in Natural Language Explanations
Myeongjun Jang, Bodhisattwa Prasad Majumder, Julian McAuley +2
While recent works have been considerably improving the quality of the natural language explanations (NLEs) generated by a model to justify its predictions, there is very limited r…
Counter-GAP: Counterfactual Bias Evaluation through Gendered Ambiguous Pronouns
Zhongbin Xie, Vid Kocijan, Thomas Lukasiewicz +1
Bias-measuring datasets play a critical role in detecting biased behavior of language models and in evaluating progress of bias mitigation methods. In this work, we focus on evalua…
Rationalizing Predictions by Adversarial Information Calibration
Lei Sha, Oana-Maria Camburu, Thomas Lukasiewicz
Explaining the predictions of AI models is paramount in safety-critical applications, such as in legal or medical domains. One form of explanation for a prediction is an extractive…
Explaining Chest X-ray Pathologies in Natural Language
Maxime Kayser, Cornelius Emde, Oana-Maria Camburu +3
Most deep learning algorithms lack explanations for their predictions, which limits their deployment in clinical practice. Approaches to improve explainability, especially in medic…
Few-Shot Out-of-Domain Transfer Learning of Natural Language Explanations in a Label-Abundant Setup
Yordan Yordanov, Vid Kocijan, Thomas Lukasiewicz +1
Training a model to provide natural language explanations (NLEs) for its predictions usually requires the acquisition of task-specific NLEs, which is time- and resource-consuming.…
Knowledge-Grounded Self-Rationalization via Extractive and Natural Language Explanations
Bodhisattwa Prasad Majumder, Oana-Maria Camburu, Thomas Lukasiewicz +1
Models that generate extractive rationales (i.e., subsets of features) or natural language explanations (NLEs) for their predictions are important for explainable AI. While an extr…