paper-with-me

Papers

LLMs are Not Just Next Token Predictors

2024-08-06 · Stephen M. Downes, Patrick Forber, Alex Grzankowski

LLMs are statistical models of language learning through stochastic gradient descent with a next token prediction objective. Prompting a popular view among AI modelers: LLMs are just next token predictors. While LLMs are engineered using next token prediction, and trained based on their success at this task, our view is that a reduction to just next token predictor sells LLMs short. Moreover, there are important explanations of LLM behavior and capabilities that are lost when we engage in this kind of reduction. In order to draw this out, we will make an analogy with a once prominent research program in biology explaining evolution and development from the gene's eye view.

📄 PDF Abstract BibTeX arXiv:2408.04666

Code (0)

등록된 구현이 없습니다.

Tasks

Prediction

Similar Papers 제목 키워드 기반

Auto-Regressive Next-Token Predictors are Universal Learners

2023-09-13 · Eran Malach

Large language models display remarkable capabilities in logical and mathematical reasoning, allowing them to solve complex tasks. Interestingly, these abilities emerge in networks trained on the simple task of next-toke…

Mathematical ReasoningText Generation

All or None: Identifiable Linear Properties of Next-token Predictors in Language Modeling

2024-10-30 · Emanuele Marconato, Sébastien Lachapelle, Sebastian Weichwald, Luigi Gresele

We analyze identifiability as a possible explanation for the ubiquity of linear properties across language models, such as the vector difference between the representations of "easy" and "easiest" being parallel to that …

AllDiversityLanguage ModelingLanguage Modelling

Large Language Models are Zero-Shot Next Location Predictors

2024-05-31 · Ciro Beneduce, Bruno Lepri, Massimiliano Luca

Predicting the locations an individual will visit in the future is crucial for solving many societal issues like disease diffusion and reduction of pollution. However, next-location predictors require a significant amoun…

Recommendation Systems

Improving Next Tokens via Second-Last Predictions with Generate and Refine

2024-11-23 · Johannes Schneider

Autoregressive language models like GPT aim at predicting next tokens, while autoencoding models such as BERT are trained on tasks such as predicting masked tokens. We train a decoder only architecture for predicting the…

Decoder

BioBlue: Systematic runaway-optimiser-like LLM failure modes on biologically and economically aligned AI safety benchmarks for LLMs with simplified observation format

2025-09-02 · Roland Pihlakas, Sruthi Susan Kuriakose arxiv

Many AI alignment discussions of "runaway optimisation" focus on RL agents: unbounded utility maximisers that over-optimise a proxy objective (e.g., "paperclip maximiser", specification gaming) at the expense of everythi…