Cover Image

Waste Not, Want Not; Recycled Gumbel Noise Improves Consistency in Natural Language Generation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	de Mijolla, Damien, Saddiq, Hannan, Moore, Kim
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Gumbel Machine: Counterfactual Student Writing Generation via Gumbel Noise Steering
by: McNichols, Hunter, et al.
Published: (2026)

Language hooks: a modular framework for augmenting LLM reasoning that decouples tool usage from the model and its prompt
by: de Mijolla, Damien, et al.
Published: (2024)

GumbelSoft: Diversified Language Model Watermarking via the GumbelMax-trick
by: Fu, Jiayi, et al.
Published: (2024)

Gumbel Counterfactual Generation From Language Models
by: Ravfogel, Shauli, et al.
Published: (2024)

Gumbel Distillation for Parallel Text Generation
by: Zhang, Chi, et al.
Published: (2026)

Universal Adversarial Suffixes Using Calibrated Gumbel-Softmax Relaxation
by: Soor, Sampriti, et al.
Published: (2025)

Improving Generalization in Semantic Parsing by Increasing Natural Language Variation
by: Saparina, Irina, et al.
Published: (2024)

Gumbel Reranking: Differentiable End-to-End Reranker Optimization
by: Huang, Siyuan, et al.
Published: (2025)

Multidimensional Consistency Improves Reasoning in Language Models
by: Lai, Huiyuan, et al.
Published: (2025)

Revisiting Noise in Natural Language Processing for Computational Social Science
by: Borenstein, Nadav
Published: (2025)

DCR-Consistency: Divide-Conquer-Reasoning for Consistency Evaluation and Improvement of Large Language Models
by: Cui, Wendi, et al.
Published: (2024)

Are Large Language Models Consistent over Value-laden Questions?
by: Moore, Jared, et al.
Published: (2024)

RETROcode: Leveraging a Code Database for Improved Natural Language to Code Generation
by: Beau, Nathanaël, et al.
Published: (2025)

Improving the Robustness of Large Language Models via Consistency Alignment
by: Zhao, Yukun, et al.
Published: (2024)

Natural Language Generation
by: Reiter, Ehud
Published: (2025)

Natural Language Generation
by: van Miltenburg, Emiel, et al.
Published: (2025)

Towards Consistent Natural-Language Explanations via Explanation-Consistency Finetuning
by: Chen, Yanda, et al.
Published: (2024)

Improving Natural Language Capability of Code Large Language Model
by: Li, Wei, et al.
Published: (2024)

RecycleGPT: An Autoregressive Language Model with Recyclable Module
by: Jiang, Yufan, et al.
Published: (2023)

Improving Faithfulness of Large Language Models in Summarization via Sliding Generation and Self-Consistency
by: Li, Taiji, et al.
Published: (2024)

Do Not Waste Your Rollouts: Recycling Search Experience for Efficient Test-Time Scaling
by: Wang, Xinglin, et al.
Published: (2026)

Judge as A Judge: Improving the Evaluation of Retrieval-Augmented Generation through the Judge-Consistency of Large Language Models
by: Liu, Shuliang, et al.
Published: (2025)

Cross-Refine: Improving Natural Language Explanation Generation by Learning in Tandem
by: Wang, Qianli, et al.
Published: (2024)

Attention Overflow: Language Model Input Blur during Long-Context Missing Items Recommendation
by: Sileo, Damien
Published: (2024)

Consistency is Key: Disentangling Label Variation in Natural Language Processing with Intra-Annotator Agreement
by: Abercrombie, Gavin, et al.
Published: (2023)

See the Unseen: Better Context-Consistent Knowledge-Editing by Noises
by: Huang, Youcheng, et al.
Published: (2024)

Human Speech Perception in Noise: Can Large Language Models Paraphrase to Improve It?
by: Chingacham, Anupama, et al.
Published: (2024)

Planning In Natural Language Improves LLM Search For Code Generation
by: Wang, Evan, et al.
Published: (2024)

Wanting to be Understood
by: Fernando, Chrisantha, et al.
Published: (2025)

Using Natural Language Explanations to Improve Robustness of In-context Learning
by: He, Xuanli, et al.
Published: (2023)

DoubleDipper: Improving Long-Context LLMs via Context Recycling
by: Cattan, Arie, et al.
Published: (2024)

Predictability and Causality in Spanish and English Natural Language Generation
by: Busto-Castiñeira, Andrea, et al.
Published: (2024)

Noise-Robust Abstractive Compression in Retrieval-Augmented Language Models
by: Kim, Singon
Published: (2025)

Noise-Driven Persona Formation in Reflexive Neural Language Generation
by: Shigemura, Toshiyuki
Published: (2025)

Impact of Preference Noise on the Alignment Performance of Generative Language Models
by: Gao, Yang, et al.
Published: (2024)

Cheetah: Natural Language Generation for 517 African Languages
by: Adebara, Ife, et al.
Published: (2024)

Natural Language Inference Improves Compositionality in Vision-Language Models
by: Cascante-Bonilla, Paola, et al.
Published: (2024)

GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling
by: Dadgarnia, Alireza, et al.
Published: (2026)

Improving Code Generation by Training with Natural Language Feedback
by: Chen, Angelica, et al.
Published: (2023)

The Generalization Ridge: Information Flow in Natural Language Generation
by: Chang, Ruidi, et al.
Published: (2025)