Related papers: Explaining black box text modules in natural langu…

Like humans, document summarization models can interpret a document's contents in a number of ways. Unfortunately, the neural models of today are largely black boxes that provide little explanation of how or why they generated a summary in…

Recent advances in natural language processing (NLP) have opened up greater opportunities to enable fine-tuned large language models (LLMs) to behave as more powerful interactive agents through improved instruction-following ability.…

Recent LLMs like DeepSeek-R1 have demonstrated state-of-the-art performance by integrating deep thinking and complex reasoning during generation. However, the internal mechanisms behind these reasoning processes remain unexplored. We…

The advent of large language models (LLMs) has significantly advanced natural language processing tasks like text summarization. However, their large size and computational demands, coupled with privacy concerns in data transmission, limit…

Language models based on the Transformer architecture achieve excellent results in many language-related tasks, such as text classification or sentiment analysis. However, despite the architecture of these models being well-defined, little…

One of the long-standing goals in optimisation and constraint programming is to describe a problem in natural language and automatically obtain an executable, efficient model. Large language models appear to bring this vision closer,…

As the use of deep learning techniques has grown across various fields over the past decade, complaints about the opaqueness of the black-box models have increased, resulting in an increased focus on transparency in deep learning models.…

Sentiment Analysis (SA) is an indispensable task for many real-world applications. Compared to limited resourced languages (i.e., Arabic, Bengali), most of the research on SA are conducted for high resourced languages (i.e., English,…

Large language models have exhibited impressive performance across a broad range of downstream tasks in natural language processing. However, how a language model predicts the next token and generates content is not generally understandable…

Masked Language Models (MLM) are self-supervised neural networks trained to fill in the blanks in a given sentence with masked tokens. Despite the tremendous success of MLMs for various text based tasks, they are not robust for spoken…

LLMs (Large Language Models) usually interact with users in the form of dialogue and generate responses following their instructions, which naturally require dialogue comprehension abilities. However, dialogue comprehension is a general…

In this paper, we explore the task of automatically generating natural language descriptions of salient patterns in a time series, such as stock prices of a company over a week. A model for this task should be able to extract high-level…

The trade-off between expressiveness and interpretability remains a core challenge when building human-centric predictive models for classification and decision-making. While symbolic rules offer interpretability, they often lack…

Generating explanations for neural networks has become crucial for their applications in real-world with respect to reliability and trustworthiness. In natural language processing, existing methods usually provide important features which…

Large language models (LLMs) have demonstrated exceptional performance not only in natural language processing tasks but also in a great variety of non-linguistic domains. In diverse optimization scenarios, there is also a rising trend of…

Large Language Models (LLMs) are becoming vital tools that help us solve and understand complex problems by acting as digital assistants. LLMs can generate convincing explanations, even when only given the inputs and outputs of these…

In search settings, calibrating the scores during the ranking process to quantities such as click-through rates or relevance levels enhances a system's usefulness and trustworthiness for downstream users. While previous research has…

To make sense of massive data, we often fit simplified models and then interpret the parameters; for example, we cluster the text embeddings and then interpret the mean parameters of each cluster. However, these parameters are often…

The era of Large Language Models (LLMs) presents a new opportunity for interpretability--agentic interpretability: a multi-turn conversation with an LLM wherein the LLM proactively assists human understanding by developing and leveraging a…

Sparse Autoencoders (SAEs) have been successfully used to probe Large Language Models (LLMs) and extract interpretable concepts from their internal representations. These concepts are linear combinations of neuron activations that…