Related papers: Can Rationalization Improve Robustness?
Reasoning LLMs (RLLMs) generate step-by-step chains of thought (CoTs) before giving an answer, which improves performance on complex tasks and makes reasoning more transparent. But how robust are these reasoning traces to disruptions that…
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 justification, a rationale, for their predictions. We approach…
Large reasoning models with reasoning capabilities achieve state-of-the-art performance on complex tasks, but their robustness under multi-turn adversarial pressure remains underexplored. We evaluate nine frontier reasoning models under…
Despite the impressive adaptability of large language models (LLMs), challenges remain in ensuring their security, transparency, and interpretability. Given their susceptibility to adversarial attacks, LLMs need to be defended with an…
Work on "learning with rationales" shows that humans providing explanations to a machine learning system can improve the system's predictive accuracy. However, this work has not been connected to work in "explainable AI" which concerns…
The task of rationalization aims to extract pieces of input text as rationales to justify neural network predictions on text classification tasks. By definition, rationales represent key text pieces used for prediction and thus should have…
State-of-the-art deep neural networks (DNNs) are highly effective at tackling many real-world tasks. However, their wide adoption in mission-critical contexts is hampered by two major weaknesses - their susceptibility to adversarial attacks…
Deep neural networks (DNNs) have had many successes, but they suffer from two major issues: (1) a vulnerability to adversarial examples and (2) a tendency to elude human interpretation. Interestingly, recent empirical and theoretical…
The reasoning steps generated by LLMs might be incomplete, as they mimic logical leaps common in everyday communication found in their pre-training data: underlying rationales are frequently left implicit (unstated). To address this…
Legal judgment prediction is the task of predicting the outcome of court cases on a given text description of facts of cases. These tasks apply Natural Language Processing (NLP) techniques to predict legal judgment results based on facts.…
Reliable deployment of machine learning models such as neural networks continues to be challenging due to several limitations. Some of the main shortcomings are the lack of interpretability and the lack of robustness against adversarial…
Building an effective adversarial attacker and elaborating on countermeasures for adversarial attacks for natural language processing (NLP) have attracted a lot of research in recent years. However, most of the existing approaches focus on…
Learning from rationales seeks to augment model prediction accuracy using human-annotated rationales (i.e. subsets of input tokens) that justify their chosen labels, often in the form of intermediate or multitask supervision. While…
Selective rationalization has become a common mechanism to ensure that predictive models reveal how they use any available features. The selection may be soft or hard, and identifies a subset of input features relevant for prediction. The…
The quality of rationales is essential in the reasoning capabilities of language models. Rationales not only enhance reasoning performance in complex natural language tasks but also justify model decisions. However, obtaining impeccable…
Neural networks have recently achieved human-level performance on various challenging natural language processing (NLP) tasks, but it is notoriously difficult to understand why a neural network produced a particular prediction. In this…
NLP models often rely on superficial cues known as dataset biases to achieve impressive performance, and can fail on examples where these biases do not hold. Recent work sought to develop robust, unbiased models by filtering biased examples…
Generating free-text rationales is among the emergent capabilities of Large Language Models (LLMs). These rationales have been found to enhance LLM performance across various NLP tasks. Recently, there has been growing interest in using…
Sensitivity of deep-neural models to input noise is known to be a challenging problem. In NLP, model performance often deteriorates with naturally occurring noise, such as spelling errors. To mitigate this issue, models may leverage…
Recent works have shown explainability and robustness are two crucial ingredients of trustworthy and reliable text classification. However, previous works usually address one of two aspects: i) how to extract accurate rationales for…