Related papers: Enhancing Post-Hoc Attributions in Long Document C…
We analyze state-of-the-art deep learning models for three tasks: question answering on (1) images, (2) tables, and (3) passages of text. Using the notion of \emph{attribution} (word importance), we find that these deep networks often…
Attribution scores indicate the importance of different input parts and can, thus, explain model behaviour. Currently, prompt-based models are gaining popularity, i.a., due to their easier adaptability in low-resource settings. However, the…
Large language models (LLMs) achieve strong performance and have revolutionized NLP, but their lack of explainability keeps them treated as black boxes, limiting their use in domains that demand transparency and trust. A promising direction…
Accurate attribution of authorship is crucial for maintaining the integrity of digital content, improving forensic investigations, and mitigating the risks of misinformation and plagiarism. Addressing the imperative need for proper…
Reasoning about information from multiple parts of a passage to derive an answer is an open challenge for reading-comprehension models. In this paper, we present an approach that reasons about complex questions by decomposing them to…
While large language models (LLMs) are equipped with longer text input capabilities than before, they are struggling to seek correct information in long contexts. The "lost in the middle" problem challenges most LLMs, referring to the…
Post-hoc explanation methods are an important class of approaches that help understand the rationale underlying a trained model's decision. But how useful are they for an end-user towards accomplishing a given task? In this vision paper, we…
Counterfactual reasoning has emerged as a crucial technique for generalizing the reasoning capabilities of large language models (LLMs). By generating and analyzing counterfactual scenarios, researchers can assess the adaptability and…
The rapid expansion of information from diverse sources has heightened the need for effective automatic text summarization, which condenses documents into shorter, coherent texts. Summarization methods generally fall into two categories:…
Text summarization aims to condense long documents and retain key information. Critical to the success of a summarization model is the faithful inference of latent representations of words or tokens in the source documents. Most recent…
Originally inspired by game-theory, path attribution framework stands out among the post-hoc model interpretation tools due to its axiomatic nature. However, recent developments show that this framework can still suffer from…
Long-form question answering (LFQA) poses a challenge as it involves generating detailed answers in the form of paragraphs, which go beyond simple yes/no responses or short factual answers. While existing QA models excel in questions with…
While large text-to-image models are able to synthesize "novel" images, these images are necessarily a reflection of the training data. The problem of data attribution in such models -- which of the images in the training set are most…
Modern generative search engines enhance the reliability of large language model (LLM) responses by providing cited evidence. However, evaluating the answer's attribution, i.e., whether every claim within the generated responses is fully…
Despite the widespread adoption of autoregressive language models, explainability evaluation research has predominantly focused on span infilling and masked language models. Evaluating the faithfulness of an explanation method -- how…
Large pre-trained language models (LMs) have been shown to perform surprisingly well when fine-tuned on tasks that require commonsense and world knowledge. However, in end-to-end architectures, it is difficult to explain what is the…
Computationally intensive decoding procedures--including search, reranking, and self-critique--can improve the quality of language model (LM) outputs in problems spanning code generation, numerical reasoning, and dialog. Existing work…
Open-domain generative systems have gained significant attention in the field of conversational AI (e.g., generative search engines). This paper presents a comprehensive review of the attribution mechanisms employed by these systems,…
Attribution theory explains how individuals interpret and attribute others' behavior in a social context by employing personal (dispositional) and impersonal (situational) causality. Large Language Models (LLMs), trained on human-generated…
HTML documents are an important medium for disseminating information on the Web for human consumption. An HTML document presents information in multiple text formats including unstructured text, structured key-value pairs, and tables.…