The End of Manual Decoding: Towards Truly End-to-End Language Models

• URL: http://arxiv.org/abs/2510.26697v2
• Date: Fri, 31 Oct 2025 17:36:35 GMT
• Title: The End of Manual Decoding: Towards Truly End-to-End Language Models
• Authors: Zhichao Wang, Dongyang Ma, Xinting Huang, Deng Cai, Tian Lan, Jiahao Xu, Haitao Mi, Xiaoying Tang, Yan Wang,
• Abstract summary: This paper introduces AutoDeco, a novel architecture that enables truly "end-to-end" generation.<n>We augment the standard transformer with lightweight heads that, at each step, dynamically predict context-specific temperature and top-p values.<n>We demonstrate that AutoDeco not only significantly outperforms default decoding strategies but also achieves performance comparable to an oracle-tuned baseline.
• Score: 45.96704867353608
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The "end-to-end" label for LLMs is a misnomer. In practice, they depend on a non-differentiable decoding process that requires laborious, hand-tuning of hyperparameters like temperature and top-p. This paper introduces AutoDeco, a novel architecture that enables truly "end-to-end" generation by learning to control its own decoding strategy. We augment the standard transformer with lightweight heads that, at each step, dynamically predict context-specific temperature and top-p values alongside the next-token logits. This approach transforms decoding into a parametric, token-level process, allowing the model to self-regulate its sampling strategy within a single forward pass. Through extensive experiments on eight benchmarks, we demonstrate that AutoDeco not only significantly outperforms default decoding strategies but also achieves performance comparable to an oracle-tuned baseline derived from "hacking the test set"-a practical upper bound for any static method. Crucially, we uncover an emergent capability for instruction-based decoding control: the model learns to interpret natural language commands (e.g., "generate with low randomness") and adjusts its predicted temperature and top-p on a token-by-token basis, opening a new paradigm for steerable and interactive LLM decoding.

Related papers

• ByteFlow: Language Modeling through Adaptive Byte Compression without a Tokenizer [17.871012556931067]
  We introduce textbfByteFlow Net, a new hierarchical architecture that removes tokenizers entirely.<n>ByteFlow Net performs compression-driven segmentation based on the coding rate of latent representations.<n>Experiments demonstrate that this chunking strategy yields substantial performance gains.
  arXiv  Detail & Related papers  (2026-03-03T23:20:31Z)
• Towards Improved Sentence Representations using Token Graphs [41.412173502714225]
  We introduce GLOT, a structure-aware pooling module that reframes pooling as relational learning followed by aggregation.<n>On a diagnostic stress test where 90% of tokens are random distractors, GLOT maintains over 97% accuracy while baseline methods collapse.<n>It is competitive with state-of-the-art techniques on benchmarks like GLUE and MTEB with 20x fewer trainable parameters and speeds up the training time by over 100x compared with parameter-efficient fine-tuning methods.
  arXiv  Detail & Related papers  (2026-03-03T09:00:01Z)
• Test-Time Alignment for Large Language Models via Textual Model Predictive Control [63.508812485566374]
  Textual Model Predictive Control (TMPC) is a novel predictive planning framework adapted for aligning Large Language Models at inference time.<n>TMPC is evaluated on three tasks with distinct segmentation properties: discourse-level translation, long-form response generation, and program synthesis.<n>Results demonstrate that TMPC consistently improves performance, highlighting the generality.
  arXiv  Detail & Related papers  (2025-02-28T07:24:33Z)
• COrAL: Order-Agnostic Language Modeling for Efficient Iterative Refinement [80.18490952057125]
  Iterative refinement has emerged as an effective paradigm for enhancing the capabilities of large language models (LLMs) on complex tasks. We propose Context-Wise Order-Agnostic Language Modeling (COrAL) to overcome these challenges. Our approach models multiple token dependencies within manageable context windows, enabling the model to perform iterative refinement internally.
  arXiv  Detail & Related papers  (2024-10-12T23:56:19Z)
• 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)
• Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models [79.41139393080736]
  Large language models (LLMs) have rapidly advanced and demonstrated impressive capabilities. In-Context Learning (ICL) and. Efficient Fine-Tuning (PEFT) are currently two mainstream methods for augmenting. LLMs to downstream tasks. We propose Reference Trustable Decoding (RTD), a paradigm that allows models to quickly adapt to new tasks without fine-tuning.
  arXiv  Detail & Related papers  (2024-09-30T10:48:20Z)
• LLM can Achieve Self-Regulation via Hyperparameter Aware Generation [88.69052513433603]
  Large Language Models (LLMs) employ diverse decoding strategies to control the generated text. Are LLMs conscious of the existence of these decoding strategies and capable of regulating themselves? We propose a novel text generation paradigm termed Hyperparameter Aware Generation (HAG)
  arXiv  Detail & Related papers  (2024-02-17T11:18:22Z)
• Guiding Large Language Models via Directional Stimulus Prompting [114.84930073977672]
  We introduce Directional Stimulus Prompting, a novel framework for guiding black-box large language models (LLMs) toward specific desired outputs. Instead of directly adjusting LLMs, our method employs a small tunable policy model to generate an auxiliary directional stimulus prompt for each input instance.
  arXiv  Detail & Related papers  (2023-02-22T17:44:15Z)
• Direction is what you need: Improving Word Embedding Compression in Large Language Models [7.736463504706344]
  This paper presents a novel loss objective to compress token embeddings in Transformer-based models by leveraging an AutoEncoder architecture. Our method significantly outperforms the commonly used SVD-based matrix-factorization approach in terms of initial language model Perplexity.
  arXiv  Detail & Related papers  (2021-06-15T14:28:00Z)

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.