Does Transformer Interpretability Transfer to RNNs?

• URL: http://arxiv.org/abs/2404.05971v1
• Date: Tue, 9 Apr 2024 02:59:17 GMT
• Title: Does Transformer Interpretability Transfer to RNNs?
• Authors: Gonçalo Paulo, Thomas Marshall, Nora Belrose,
• Abstract summary: Recent advances in recurrent neural network architectures have enabled RNNs to match or exceed the performance of equal-size transformers. We show that it is possible to improve some of these techniques by taking advantage of RNNs' compressed state.
• Score: 0.6437284704257459
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advances in recurrent neural network architectures, such as Mamba and RWKV, have enabled RNNs to match or exceed the performance of equal-size transformers in terms of language modeling perplexity and downstream evaluations, suggesting that future systems may be built on completely new architectures. In this paper, we examine if selected interpretability methods originally designed for transformer language models will transfer to these up-and-coming recurrent architectures. Specifically, we focus on steering model outputs via contrastive activation addition, on eliciting latent predictions via the tuned lens, and eliciting latent knowledge from models fine-tuned to produce false outputs under certain conditions. Our results show that most of these techniques are effective when applied to RNNs, and we show that it is possible to improve some of them by taking advantage of RNNs' compressed state.

Related papers

• Autoregressive + Chain of Thought = Recurrent: Recurrence's Role in Language Models' Computability and a Revisit of Recurrent Transformer [29.970200877158764]
  We investigate the influence of recurrent structures in neural models on their reasoning abilities and computability. We shed light on how the CoT approach can mimic recurrent computation and act as a bridge between autoregression and recurrence.
  arXiv  Detail & Related papers  (2024-09-14T00:30:57Z)
• NAR-Former V2: Rethinking Transformer for Universal Neural Network Representation Learning [25.197394237526865]
  We propose a modified Transformer-based universal neural network representation learning model NAR-Former V2. Specifically, we take the network as a graph and design a straightforward tokenizer to encode the network into a sequence. We incorporate the inductive representation learning capability of GNN into Transformer, enabling Transformer to generalize better when encountering unseen architecture.
  arXiv  Detail & Related papers  (2023-06-19T09:11:04Z)
• RWKV: Reinventing RNNs for the Transformer Era [54.716108899349614]
  We propose a novel model architecture that combines the efficient parallelizable training of transformers with the efficient inference of RNNs. We scale our models as large as 14 billion parameters, by far the largest dense RNN ever trained, and find RWKV performs on par with similarly sized Transformers.
  arXiv  Detail & Related papers  (2023-05-22T13:57:41Z)
• Return of the RNN: Residual Recurrent Networks for Invertible Sentence Embeddings [0.0]
  This study presents a novel model for invertible sentence embeddings using a residual recurrent network trained on an unsupervised encoding task. Rather than the probabilistic outputs common to neural machine translation models, our approach employs a regression-based output layer to reconstruct the input sequence's word vectors. The model achieves high accuracy and fast training with the ADAM, a significant finding given that RNNs typically require memory units, such as LSTMs, or second-order optimization methods.
  arXiv  Detail & Related papers  (2023-03-23T15:59:06Z)
• Full Stack Optimization of Transformer Inference: a Survey [58.55475772110702]
  Transformer models achieve superior accuracy across a wide range of applications. The amount of compute and bandwidth required for inference of recent Transformer models is growing at a significant rate. There has been an increased focus on making Transformer models more efficient.
  arXiv  Detail & Related papers  (2023-02-27T18:18:13Z)
• NAR-Former: Neural Architecture Representation Learning towards Holistic Attributes Prediction [37.357949900603295]
  We propose a neural architecture representation model that can be used to estimate attributes holistically. Experiment results show that our proposed framework can be used to predict the latency and accuracy attributes of both cell architectures and whole deep neural networks.
  arXiv  Detail & Related papers  (2022-11-15T10:15:21Z)
• VQ-T: RNN Transducers using Vector-Quantized Prediction Network States [52.48566999668521]
  We propose to use vector-quantized long short-term memory units in the prediction network of RNN transducers. By training the discrete representation jointly with the ASR network, hypotheses can be actively merged for lattice generation. Our experiments on the Switchboard corpus show that the proposed VQ RNN transducers improve ASR performance over transducers with regular prediction networks.
  arXiv  Detail & Related papers  (2022-08-03T02:45:52Z)
• Pretraining Graph Neural Networks for few-shot Analog Circuit Modeling and Design [68.1682448368636]
  We present a supervised pretraining approach to learn circuit representations that can be adapted to new unseen topologies or unseen prediction tasks. To cope with the variable topological structure of different circuits we describe each circuit as a graph and use graph neural networks (GNNs) to learn node embeddings. We show that pretraining GNNs on prediction of output node voltages can encourage learning representations that can be adapted to new unseen topologies or prediction of new circuit level properties.
  arXiv  Detail & Related papers  (2022-03-29T21:18:47Z)
• CSformer: Bridging Convolution and Transformer for Compressive Sensing [65.22377493627687]
  This paper proposes a hybrid framework that integrates the advantages of leveraging detailed spatial information from CNN and the global context provided by transformer for enhanced representation learning. The proposed approach is an end-to-end compressive image sensing method, composed of adaptive sampling and recovery. The experimental results demonstrate the effectiveness of the dedicated transformer-based architecture for compressive sensing.
  arXiv  Detail & Related papers  (2021-12-31T04:37:11Z)
• Coupled Oscillatory Recurrent Neural Network (coRNN): An accurate and (gradient) stable architecture for learning long time dependencies [15.2292571922932]
  We propose a novel architecture for recurrent neural networks. Our proposed RNN is based on a time-discretization of a system of second-order ordinary differential equations. Experiments show that the proposed RNN is comparable in performance to the state of the art on a variety of benchmarks.
  arXiv  Detail & Related papers  (2020-10-02T12:35:04Z)
• Pretraining Techniques for Sequence-to-Sequence Voice Conversion [57.65753150356411]
  Sequence-to-sequence (seq2seq) voice conversion (VC) models are attractive owing to their ability to convert prosody. We propose to transfer knowledge from other speech processing tasks where large-scale corpora are easily available, typically text-to-speech (TTS) and automatic speech recognition (ASR) We argue that VC models with such pretrained ASR or TTS model parameters can generate effective hidden representations for high-fidelity, highly intelligible converted speech.
  arXiv  Detail & Related papers  (2020-08-07T11:02:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.