paper-with-me

홈 › Papers

Simplifying the Modeling of Arbitrary Conditionals in Natural Language

2026-06-12 · Yinhan Lu, Eric Elmoznino, Léo Gagnon, Sarthak Mittal, Tejas Kasetty, Guillaume Lajoie arxiv

Causal Transformers model sequences through an autoregressive factorization of the joint distribution, which enables efficient left-to-right decoding and conditional likelihood computation. However, they cannot tractably sample from or evaluate arbitrary conditionals -- e.g., a block of text conditioned on past and future tokens. Recent work aims to solve this problem through novel architectures, but they often lead to sub-optimal modeling of such conditionals and degraded generations. We propose Arbitrary Conditionals GPT (AC-GPT) which introduces a simple modification to standard causal Transformers to enable evaluating and sampling from arbitrary conditionals -- including past, future, and mixed contexts -- within a single forward pass. Unlike prior approaches, our method preserves the standard left-to-right ordering and next-token prediction objective essential for both strong performance and efficient training on natural language. Crucially, this compatibility allows existing LLMs to be fine-tuned for arbitrary conditioning. Our empirical results indicate that our method outperforms baselines on modeling arbitrary conditionals, without degrading standard left-to-right performance.

📄 PDF Abstract BibTeX arXiv:2606.14943

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Training and Inference on Any-Order Autoregressive Models the Right Way

2022-05-26 · Andy Shih, Dorsa Sadigh, Stefano Ermon

Conditional inference on arbitrary subsets of variables is a core problem in probabilistic inference with important applications such as masked language modeling and image inpainting. In recent years, the family of Any-O…

Image InpaintingLanguage ModelingLanguage ModellingMasked Language Modeling

Path-Dependent Denoising: A Non-Conservative Field Perspective on Order Collapse in Diffusion Language Models

2026-05-10 · Jeonseong Kim arxiv

Diffusion language models (DLMs) offer a structural alternative to autoregressive generation: denoising can update tokens in arbitrary orders or in parallel rather than along a fixed left-to-right chain. In practice, fas…

Probabilistic modeling of rational communication with conditionals

2021-05-12 · Britta Grusdt, Daniel Lassiter, Michael Franke

While a large body of work has scrutinized the meaning of conditional sentences, considerably less attention has been paid to formal models of their pragmatic use and interpretation. Here, we take a probabilistic approac…

On The Chain Rule Optimal Transport Distance

2018-12-19 · Frank Nielsen, Ke Sun

We define a novel class of distances between statistical multivariate distributions by modeling an optimal transport problem on their marginals with respect to a ground distance defined on their conditionals. These new d…

Arbitrary Conditional Distributions with Energy

2021-02-08 · NeurIPS 2021 12 · Ryan R. Strauss, Junier B. Oliva

Modeling distributions of covariates, or density estimation, is a core challenge in unsupervised learning. However, the majority of work only considers the joint distribution, which has limited utility in practical situa…

Arbitrary Conditional Density EstimationImputation