paper-with-me

홈 › Papers

Limitations of Autoregressive Models and Their Alternatives

2020-10-22 · NAACL 2021 4 · Chu-Cheng Lin, Aaron Jaech, Xin Li, Matthew R. Gormley, Jason Eisner

Standard autoregressive language models perform only polynomial-time computation to compute the probability of the next symbol. While this is attractive, it means they cannot model distributions whose next-symbol probability is hard to compute. Indeed, they cannot even model them well enough to solve associated easy decision problems for which an engineer might want to consult a language model. These limitations apply no matter how much computation and data are used to train the model, unless the model is given access to oracle parameters that grow superpolynomially in sequence length. Thus, simply training larger autoregressive language models is not a panacea for NLP. Alternatives include energy-based models (which give up efficient sampling) and latent-variable autoregressive models (which give up efficient scoring of a given string). Both are powerful enough to escape the above limitations.

📄 PDF Abstract BibTeX arXiv:2010.11939

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage Modelling

Similar Papers 제목 키워드 기반

Alternatives To Next Token Prediction In Text Generation -- A Survey

2025-09-29 · Charlie Wyatt, Aditya Joshi, Flora Salim arxiv

The paradigm of Next Token Prediction (NTP) has driven the unprecedented success of Large Language Models (LLMs), but is also the source of their most persistent weaknesses such as poor long-term planning, error accumula…

Text Generation

Analyzing Diffusion and Autoregressive Vision Language Models in Multimodal Embedding Space

2026-01-19 · Zihang Wang, Siyue Zhang, Yilun Zhao, Jingyi Yang 외 arxiv

Embedding models are a fundamental component of modern AI systems such as semantic search and retrieval-augmented generation. Recent advances in large foundation models have substantially accelerated the development of e…

Visual Question AnsweringInformation Retrieval

Translating Images to Road Network: A Non-Autoregressive Sequence-to-Sequence Approach

2023-01-01 · ICCV 2023 1 · Jiachen Lu, Renyuan Peng, Xinyue Cai, Hang Xu 외

The extraction of road network is essential for the generation of high-definition maps since it enables the precise localization of road landmarks and their interconnections. However, generating road network poses a …

Incorporating Reinforced Adversarial Learning in Autoregressive Image Generation

2020-07-20 · ECCV 2020 8 · Kenan E. Ak, Ning Xu, Zhe Lin, Yilin Wang

Autoregressive models recently achieved comparable results versus state-of-the-art Generative Adversarial Networks (GANs) with the help of Vector Quantized Variational AutoEncoders (VQ-VAE). However, autoregressive model…

Image Generation

GEC-DePenD: Non-Autoregressive Grammatical Error Correction with Decoupled Permutation and Decoding

2023-11-14 · Konstantin Yakovlev, Alexander Podolskiy, Andrey Bout, Sergey Nikolenko 외

Grammatical error correction (GEC) is an important NLP task that is currently usually solved with autoregressive sequence-to-sequence models. However, approaches of this class are inherently slow due to one-by-one token …

DecoderDenoisingGrammatical Error CorrectionSynthetic Data Generation