Conditional Attribute Estimation with Autoregressive Sequence Models

• URL: http://arxiv.org/abs/2605.14004v1
• Date: Wed, 13 May 2026 18:11:16 GMT
• Title: Conditional Attribute Estimation with Autoregressive Sequence Models
• Abstract summary: Conditional Attribute Transformers is a novel method for jointly estimating the next-token probability and the value of an attribute on each potential next token selection.<n>Our approach achieves state of the art performance on sparse reward tasks, estimates attribute probabilities orders of magnitude faster than sampling, and can guide decoding of autoregressive sequence models on a range of language tasks.
• Score: 2.956641142618867
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Generative models are often trained with a next-token prediction objective, yet many downstream applications require the ability to estimate or control sequence-level properties. Next-token prediction can lead to overfitting of local patterns during training, underfitting of global structure, and requires significant downstream modifications or expensive sampling to guide or predict the global attributes of generated samples at inference time. Here, we introduce Conditional Attribute Transformers, a novel method for jointly estimating the next-token probability and the value of an attribute conditional on each potential next token selection. This framework enables three critical capabilities within a single forward pass, without modification of the input sequence: (1) per-token credit assignment across an entire sequence, by identifying how each token in a sequence is associated with an attribute's value; (2) counterfactual analysis, by quantifying attribute differences conditional on alternative next token choices; (3) steerable generation, by decoding sequences based on a combination of next-token and attribute likelihoods. Our approach achieves state of the art performance on sparse reward tasks, improves next-token prediction at sufficient model sizes, estimates attribute probabilities orders of magnitude faster than sampling, and can guide decoding of autoregressive sequence models on a range of language tasks.

Related papers

• Sample Is Feature: Beyond Item-Level, Toward Sample-Level Tokens for Unified Large Recommender Models [14.332200648147863]
  We propose textbfSIF (emphSample Is Feature), which encodes each historical Raw Sample directly into the sequence token.<n>The textbfSample Tokenizer quantizes each historical Raw Sample into a Token Sample via hierarchical group-adaptive quantization.<n>The textbfSIF-Mixer performs deep feature interaction over the homogeneous sample representations via token-level and sample-level mixing, fully unleashing the model's representational capacity.
  arXiv  Detail & Related papers  (2026-04-17T02:47:31Z)
• Enhancing next token prediction based pre-training for jet foundation models [0.0]
  Next token prediction is an attractive pre-training task for jet foundation models.<n>It is simulation free and enables excellent generative capabilities that can transfer across datasets.
  arXiv  Detail & Related papers  (2025-12-03T19:00:00Z)
• MergeDNA: Context-aware Genome Modeling with Dynamic Tokenization through Token Merging [65.07273789940116]
  This paper introduces a hierarchical architecture that jointly optimize a dynamic genomic tokenizer and latent Transformers with context-aware pre-training tasks.<n> MergeDNA achieves superior performance on three popular DNA benchmarks and several multi-omics tasks with fine-tuning or zero-shot evaluation.
  arXiv  Detail & Related papers  (2025-11-17T19:27:41Z)
• Pre-training Generative Recommender with Multi-Identifier Item Tokenization [78.87007819266957]
  We propose MTGRec to augment token sequence data for Generative Recommender pre-training.<n>Our approach involves two key innovations: multi-identifier item tokenization and curriculum recommender pre-training.<n>Extensive experiments on three public benchmark datasets demonstrate that MTGRec significantly outperforms both traditional and generative recommendation baselines.
  arXiv  Detail & Related papers  (2025-04-06T08:03:03Z)
• Enhancing Foundation Models for Time Series Forecasting via Wavelet-based Tokenization [74.3339999119713]
  We develop a wavelet-based tokenizer that allows models to learn complex representations directly in the space of time-localized frequencies.<n>Our method first scales and decomposes the input time series, then thresholds and quantizes the wavelet coefficients, and finally pre-trains an autoregressive model to forecast coefficients for the forecast horizon.
  arXiv  Detail & Related papers  (2024-12-06T18:22:59Z)
• Faster Language Models with Better Multi-Token Prediction Using Tensor Decomposition [5.575078692353885]
  We propose a new model for multi-token prediction in transformers, aiming to enhance sampling efficiency without compromising accuracy.<n>By generalizing it to a rank-$r$ canonical probability decomposition, we develop an improved model that predicts multiple tokens simultaneously.
  arXiv  Detail & Related papers  (2024-10-23T11:06:36Z)
• Exact Byte-Level Probabilities from Tokenized Language Models for FIM-Tasks and Model Ensembles [23.134664392314264]
  Tokenization is associated with many poorly understood shortcomings in language models (LMs)<n>This work studies how tokenization impacts model performance by analyzing and comparing models with their byte-level counterparts.<n>We introduce the Byte-Token Representation Lemma, a framework that establishes a mapping between the learned token distribution and its equivalent byte-level distribution.
  arXiv  Detail & Related papers  (2024-10-11T23:30:42Z)
• Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion [61.03681839276652]
  Diffusion Forcing is a new training paradigm where a diffusion model is trained to denoise a set of tokens with independent per-token noise levels.<n>We apply Diffusion Forcing to sequence generative modeling by training a causal next-token prediction model to generate one or several future tokens.
  arXiv  Detail & Related papers  (2024-07-01T15:43:25Z)
• σ-GPTs: A New Approach to Autoregressive Models [19.84252724050016]
  We show that by simply adding a positional encoding for the output, this order can be modulated on-the-fly per-sample. We evaluate our method across various domains, including language modeling, path-solving, and aircraft vertical rate prediction.
  arXiv  Detail & Related papers  (2024-04-15T08:22:47Z)
• Complex Event Forecasting with Prediction Suffix Trees: Extended Technical Report [70.7321040534471]
  Complex Event Recognition (CER) systems have become popular in the past two decades due to their ability to "instantly" detect patterns on real-time streams of events. There is a lack of methods for forecasting when a pattern might occur before such an occurrence is actually detected by a CER engine. We present a formal framework that attempts to address the issue of Complex Event Forecasting.
  arXiv  Detail & Related papers  (2021-09-01T09:52:31Z)
• Document Ranking with a Pretrained Sequence-to-Sequence Model [56.44269917346376]
  We show how a sequence-to-sequence model can be trained to generate relevance labels as "target words" Our approach significantly outperforms an encoder-only model in a data-poor regime.
  arXiv  Detail & Related papers  (2020-03-14T22:29:50Z)

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.