Cover Image

TRACE Back from the Future: A Probabilistic Reasoning Approach to Controllable Language Generation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Weng, Gwen Yidou, Wang, Benjie, Broeck, Guy Van den
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Learning Tractable Distributions Of Language Model Continuations
by: Yidou-Weng, Gwen, et al.
Published: (2025)

On the Relationship Between Monotone and Squared Probabilistic Circuits
by: Wang, Benjie, et al.
Published: (2024)

Where is the signal in tokenization space?
by: Geh, Renato Lui, et al.
Published: (2024)

Controllable Generation via Locally Constrained Resampling
by: Ahmed, Kareem, et al.
Published: (2024)

Restructuring Tractable Probabilistic Circuits
by: Zhang, Honghua, et al.
Published: (2024)

Probabilistic Circuits for Cumulative Distribution Functions
by: Broadrick, Oliver, et al.
Published: (2024)

Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models
by: Zhao, Siyan, et al.
Published: (2024)

How to Marginalize in Causal Structure Learning?
by: Zhao, William, et al.
Published: (2025)

Enabling Autoregressive Models to Fill In Masked Tokens
by: Israel, Daniel, et al.
Published: (2025)

ExplainFuzz: Explainable and Constraint-Conditioned Test Generation with Probabilistic Circuits
by: Baiget, Annaëlle, et al.
Published: (2026)

A Pseudo-Semantic Loss for Autoregressive Models with Logical Constraints
by: Ahmed, Kareem, et al.
Published: (2023)

Scaling Probabilistic Circuits via Monarch Matrices
by: Zhang, Honghua, et al.
Published: (2025)

Accelerating Diffusion LLMs via Adaptive Parallel Decoding
by: Israel, Daniel, et al.
Published: (2025)

Tractable Transformers for Flexible Conditional Generation
by: Liu, Anji, et al.
Published: (2025)

Adversarial Tokenization
by: Geh, Renato Lui, et al.
Published: (2025)

A Compositional Atlas for Algebraic Circuits
by: Wang, Benjie, et al.
Published: (2024)

Scaling Tractable Probabilistic Circuits: A Systems Perspective
by: Liu, Anji, et al.
Published: (2024)

Rethinking Probabilistic Circuit Parameter Learning
by: Liu, Anji, et al.
Published: (2025)

Breaking the Factorization Barrier in Diffusion Language Models
by: Li, Ian, et al.
Published: (2026)

Scaling Up Probabilistic Circuits by Latent Variable Distillation
by: Liu, Anji, et al.
Published: (2022)

TRACE: TRansformer-based Attribution using Contrastive Embeddings in LLMs
by: Wang, Cheng, et al.
Published: (2024)

Towards Logically Consistent Language Models via Probabilistic Reasoning
by: Calanzone, Diego, et al.
Published: (2024)

Probabilistically Rewired Message-Passing Neural Networks
by: Qian, Chendi, et al.
Published: (2023)

Image Inpainting via Tractable Steering of Diffusion Models
by: Liu, Anji, et al.
Published: (2023)

ProbMoE: Differentiable Probabilistic Routing for Mixture-of-Experts
by: Zhao, Heng, et al.
Published: (2026)

Semi-parametric Expert Bayesian Network Learning with Gaussian Processes and Horseshoe Priors
by: Weng, Yidou, et al.
Published: (2024)

Back to Basics: Revisiting Exploration in Reinforcement Learning for LLM Reasoning via Generative Probabilities
by: Li, Pengyi, et al.
Published: (2026)

Verifier-Backed Hard Problem Generation for Mathematical Reasoning
by: Lai, Yuhang, et al.
Published: (2026)

FutureGen: A RAG-based Approach to Generate the Future Work of Scientific Article
by: Azher, Ibrahim Al, et al.
Published: (2025)

Probabilistic Programs of Thought
by: Garg, Poorva, et al.
Published: (2026)

Adaptable Logical Control for Large Language Models
by: Zhang, Honghua, et al.
Published: (2024)

Collapsed Inference for Bayesian Deep Learning
by: Zeng, Zhe, et al.
Published: (2023)

Probabilistic Soundness Guarantees in LLM Reasoning Chains
by: You, Weiqiu, et al.
Published: (2025)

Probabilistic Reasoning with LLMs for k-anonymity Estimation
by: Zheng, Jonathan, et al.
Published: (2025)

Active Preference Inference using Language Models and Probabilistic Reasoning
by: Piriyakulkij, Wasu Top, et al.
Published: (2023)

Complexity Control Facilitates Reasoning-Based Compositional Generalization in Transformers
by: Zhang, Zhongwang, et al.
Published: (2025)

Generalization v.s. Memorization: Tracing Language Models' Capabilities Back to Pretraining Data
by: Wang, Xinyi, et al.
Published: (2024)

Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models
by: Zheng, Huaixiu Steven, et al.
Published: (2023)

FBQuant: FeedBack Quantization for Large Language Models
by: Liu, Yijiang, et al.
Published: (2025)

Generalized Probabilistic Attention Mechanism in Transformers
by: Heo, DongNyeong, et al.
Published: (2024)