The field of natural language processing is moving towards increased transparency and interpretability, with a focus on developing methods to explain and understand the decisions made by language models. Researchers are working on creating frameworks to evaluate the effectiveness of highlight explanations in context utilization, as well as developing novel approaches to provide actionable language feedback in applications such as sports biomechanics. Additionally, there is a growing interest in conditional representation learning, which aims to extract representations tailored to specific user-specified criteria. Noteworthy papers in this area include: Evaluation Framework for Highlight Explanations of Context Utilisation in Language Models, which introduces a gold standard evaluation framework for context attribution. Conditional Representation Learning for Customized Tasks, which proposes a method to extract representations tailored to arbitrary user-specified criteria. Learning to Interpret Weight Differences in Language Models, which introduces a method to train models to describe their own finetuning-induced modifications. Semantic Regexes: Auto-Interpreting LLM Features with a Structured Language, which introduces semantic regexes, structured language descriptions of LLM features.