Related papers: Inseq: An Interpretability Toolkit for Sequence Ge…

Machine learning algorithms often assume that training samples are independent. When data points are connected by a network, the induced dependency between samples is both a challenge, reducing effective sample size, and an opportunity to…

To harness the power of large language models in safety-critical domains, we need to ensure the explainability of their predictions. However, despite the significant attention to model interpretability, there remains an unexplored domain in…

Interpretability is a topic that has been in the spotlight for the past few years. Most existing interpretability techniques produce interpretations in the form of rules or feature importance. These interpretations, while informative, may…

Recent research in mechanistic interpretability has attempted to reverse-engineer Transformer models by carefully inspecting network weights and activations. However, these approaches require considerable manual effort and still fall short…

Pretrained transformer-based Language Models (LMs) are well-known for their ability to achieve significant improvement on NLP tasks, but their black-box nature, which leads to a lack of interpretability, has been a major concern. My…

Missing sentence generation (or sentence infilling) fosters a wide range of applications in natural language generation, such as document auto-completion and meeting note expansion. This task asks the model to generate intermediate missing…

The large success of deep learning based methods in Visual Question Answering (VQA) has concurrently increased the demand for explainable methods. Most methods in Explainable Artificial Intelligence (XAI) focus on generating post-hoc…

Since the dynamic characteristics of knowledge graphs, many inductive knowledge graph representation learning (KGRL) works have been proposed in recent years, focusing on enabling prediction over new entities. NeuralKG-ind is the first…

Data of sequential nature arise in many application domains in forms of, e.g. textual data, DNA sequences, and software execution traces. Different research disciplines have developed methods to learn sequence models from such datasets: (i)…

Neural sequence-to-sequence models are finding increasing use in editing of documents, for example in correcting a text document or repairing source code. In this paper, we argue that common seq2seq models (with a facility to copy single…

In sequence-to-sequence learning, e.g., natural language generation, the decoder relies on the attention mechanism to efficiently extract information from the encoder. While it is common practice to draw information from only the last…

Neural text generation models are typically trained by maximizing log-likelihood with the sequence cross entropy (CE) loss, which encourages an exact token-by-token match between a target sequence with a generated sequence. Such training…

Controllable generative sequence models with the capability to extract and replicate the style of specific examples enable many applications, including narrating audiobooks in different voices, auto-completing and auto-correcting written…

The sequence-to-sequence (Seq2Seq) approach has recently been widely used in grammatical error correction (GEC) and shows promising performance. However, the Seq2Seq GEC approach still suffers from two issues. First, a Seq2Seq GEC model can…

We study lossless acceleration for seq2seq generation with a novel decoding algorithm -- Aggressive Decoding. Unlike the previous efforts (e.g., non-autoregressive decoding) speeding up seq2seq generation at the cost of quality loss, our…

Deep generative models, while revolutionizing fields like image and text generation, largely operate as opaque ``black boxes'', hindering human understanding, control, and alignment. While methods like sparse autoencoders (SAEs) show…

In recent years, deep generative models have attracted increasing interest due to their capacity to model complex distributions. Among those models, variational autoencoders have gained popularity as they have proven both to be…

Knowledge-enhanced text generation aims to enhance the quality of generated text by utilizing internal or external knowledge sources. While language models have demonstrated impressive capabilities in generating coherent and fluent text,…

Inspired by the recent evolution of deep neural networks (DNNs) in machine learning, we explore their application to PL-related topics. This paper is the first step towards this goal; we propose a proof-synthesis method for the…

Understanding the internal representations of large language models (LLMs) is a central challenge in interpretability research. Existing feature interpretability methods often rely on strong assumptions about the structure of…