Understanding Token Probability Encoding in Output Embeddings
In this paper, we investigate the output token probability information in the output embedding of language models. We find an approximate common log-linear encoding of output token probabilities within the output embedding vectors and empirically demonstrate that it is accurate and sparse. As a causality examination, we steer the encoding in output embedding to modify the output probability distribution accurately. Moreover, the sparsity we find in output probability encoding suggests that a large number of dimensions in the output embedding do not contribute to causal language modeling. Therefore, we attempt to delete the output-unrelated dimensions and find more than 30% of the dimensions can be deleted without significant movement in output distribution and sequence generation. Additionally, in the pre-training dynamics of language models, we find that the output embeddings capture the corpus token frequency information in early steps, even before an obvious convergence of parameters starts.
Code (0)
등록된 구현이 없습니다.
Tasks
Causal Language ModelingLanguage ModelingLanguage ModellingSimilar Papers 제목 키워드 기반
Language Models over Canonical Byte-Pair Encodings
Modern language models represent probability distributions over character strings as distributions over (shorter) token strings derived via a deterministic tokenizer, such as byte-pair encoding. While this approach is hi…
validDo Llamas Work in English? On the Latent Language of Multilingual Transformers
We ask whether multilingual language models trained on unbalanced, English-dominated corpora use English as an internal pivot language -- a question of key importance for understanding how language models function and th…
Phase Diagram of Vision Large Language Models Inference: A Perspective from Interaction across Image and Instruction
Vision Large Language Models (VLLMs) usually take input as a concatenation of image token embeddings and text token embeddings and conduct causal modeling. However, their internal behaviors remain underexplored, raising …
multimodal interactionPseudo-Masked Language Models for Unified Language Model Pre-Training
We propose to pre-train a unified language model for both autoencoding and partially autoregressive language modeling tasks using a novel training procedure, referred to as a pseudo-masked language model (PMLM). Given an…
DecoderLanguage ModelingLanguage ModellingNatural Language Understanding+1UniLMv2: Pseudo-Masked Language Models for Unified Language Model Pre-Training
We propose to pre-train a unified language model for both autoencoding and partially autoregressive language modeling tasks using a novel training procedure, referred to as a pseudo-masked language model (PMLM). Given an…
Abstractive Text SummarizationDecoderLanguage ModelingLanguage Modelling+3