Related papers: Neuron-Level Knowledge Attribution in Large Langua…
While large language models (LLMs) have demonstrated superior multi-task capabilities, understanding the learning mechanisms behind this is still a challenging problem. In this paper, we attempt to understand such mechanisms from the…
Multilingual neural machine translation with a single model has drawn much attention due to its capability to deal with multiple languages. However, the current multilingual translation paradigm often makes the model tend to preserve the…
Given the prevalence of large language models (LLMs) and the prohibitive cost of training these models from scratch, dynamically forgetting specific knowledge e.g., private or proprietary, without retraining the model has become an…
Attributing the output of a neural network to the contribution of given input elements is a way of shedding light on the black-box nature of neural networks. Due to the complexity of current network architectures, current gradient-based…
Interpreting complex neural networks is crucial for understanding their decision-making processes, particularly in applications where transparency and accountability are essential. This proposed method addresses this need by focusing on…
Post-hoc importance attribution methods are a popular tool for "explaining" Deep Neural Networks (DNNs) and are inherently based on the assumption that the explanations can be applied independently of how the models were trained.…
This paper proposes a novel framework for recurrent neural networks (RNNs) inspired by the human memory models in the field of cognitive neuroscience to enhance information processing and transmission between adjacent RNNs' units. The…
We report on a series of experiments with convolutional neural networks (CNN) trained on top of pre-trained word vectors for sentence-level classification tasks. We show that a simple CNN with little hyperparameter tuning and static vectors…
Deep neural networks (DNNs) have demonstrated remarkable success, yet their wide adoption is often hindered by their opaque decision-making. To address this, attribution methods have been proposed to assign relevance values to each part of…
Neural retrievers are effective but brittle: underspecified or ambiguous queries can misdirect ranking even when relevant documents exist. Existing approaches address this brittleness only partially: LLMs rewrite queries without retriever…
Authorship attribution is the process of identifying the author of a text. Approaches to tackling it have been conventionally divided into classification-based ones, which work well for small numbers of candidate authors, and…
Large language models (LLMs) demonstrate strong capabilities in in-context learning, but verifying the correctness of their generated responses remains a challenge. Prior work has explored attribution at the sentence level, but these…
Regular updates are essential for maintaining up-to-date knowledge in large language models (LLMs). Consequently, various model editing methods have been developed to update specific knowledge within LLMs. However, training-based approaches…
Deep learning methods have shown great promise in many practical applications, ranging from speech recognition, visual object recognition, to text processing. However, most of the current deep learning methods suffer from scalability…
With the remarkable success of deep neural networks, there is a growing interest in research aimed at providing clear interpretations of their decision-making processes. In this paper, we introduce Attribution Equilibrium, a novel method to…
Recent studies show that LLM hidden states encode reward-related information, such as answer correctness and model confidence. However, existing approaches typically fit black-box probes on the full hidden states, offering little insight…
Understanding the internal dynamics of Recurrent Neural Networks (RNNs) is crucial for advancing their interpretability and improving their design. This study introduces an innovative information-theoretic method to identify and analyze…
To solve the problem that convolutional neural networks (CNNs) are difficult to process non-grid type relational data like graphs, Kipf et al. proposed a graph convolutional neural network (GCN). The core idea of the GCN is to perform…
Large language models have achieved near-expert performance in structured reasoning domains like mathematics and programming, yet their ability to perform compositional multi-hop reasoning in specialized scientific fields remains limited.…
Deep learning has become the workhorse for a wide range of natural language processing applications. But much of the success of deep learning relies on annotated examples. Annotation is time-consuming and expensive to produce at scale. Here…