PRAGWORLD: A Benchmark Evaluating LLMs’ Local World Model Under Minimal Linguistic Alterations and Conversational Dynamics

Code prompting elicits conditional reasoning abilities in text+ code llms

Out-of-distribution detection by leveraging between-layer transformation smoothness

CATfOOD: Counterfactual augmented training for improving out-of-domain performance and calibration

Easy to Decide, Hard to Agree: Reducing Disagreements Between Saliency Methods

Easy to Decide, Hard to Agree: Reducing Disagreements Between Saliency Methods

Toward Practical Usage of the Attention Mechanism as a Tool for Interpretability

Staying True to Your Word: (How) Can Attention Become Explanation?

Iterative Recursive Attention Model for Interpretable Sequence Classification

Predicting News Values from Headline Text and Emotions

Two Layers of Annotation for Representing Event Mentions in News Stories

Takelab at SemEval-2017 task 5: Linear aggregation of word embeddings for fine-grained sentiment analysis of financial news

Detecting and Ranking Conceptual Links between Texts Using a Knowledge Base

TakeLab at SemEval-2016 Task 6: Stance Classification in Tweets Using a Genetic Algorithm Based Ensemble