Let's Fuse Step by Step: A Generative Fusion Decoding Algorithm with LLMs for Robust and Instruction-Aware ASR and OCR

• URL: http://arxiv.org/abs/2405.14259v4
• Date: Wed, 11 Jun 2025 17:09:58 GMT
• Title: Let's Fuse Step by Step: A Generative Fusion Decoding Algorithm with LLMs for Robust and Instruction-Aware ASR and OCR
• Abstract summary: "Generative Fusion Decoding" (GFD) is designed to integrate large language models into cross-modal text recognition systems.<n>We derive the necessary formulations to enable GFD to operate across mismatched token spaces of different models.<n>GFD is plug-and-play by design, making it readily compatible with various auto-regressive models.
• Score: 13.759053227199106
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We propose "Generative Fusion Decoding" (GFD), a novel shallow fusion framework designed to integrate large language models (LLMs) into cross-modal text recognition systems for automatic speech recognition (ASR) and optical character recognition (OCR). We derive the necessary formulations to enable GFD to operate across mismatched token spaces of different models by calculating likelihood at the byte level, thereby enabling seamless fusion and synchronous progression during the decoding process. GFD is plug-and-play by design, making it readily compatible with various auto-regressive models without the need for any re-training. GFD proves effective for general ASR and OCR tasks through intermediate and frequent interactions with LLMs, surpassing cascaded methods in English and Mandarin benchmarks. In addition, GFD transfers in-context learning abilities of LLMs and allows for adaptive ASR in instruction-aware and long-context settings, yielding significant WER reductions of up to 17.7\%.

Related papers

• When LLMs Develop Languages: Symbolic Communication for Efficient Multi-Agent Reasoning [85.36421257648294]
  Chain-of-Thought (CoT) improves large language models (LLMs) on difficult reasoning tasks.<n>We propose Communicative Language Symbolism Routing (R)<n>R treats each Language Symbolism Framework as a reusable symbolic protocol with compact symbols, usage rules, and a message-passing contract.<n>R reduces latency-oriented generated token completion by $3sim 6times$ compared to standard CoT.
  arXiv  Detail & Related papers  (2026-06-28T12:02:42Z)
• FLARE: Diffusion for Hybrid Language Model [72.60770374799634]
  FLARE is a systematic conversion framework for hybrid-attention large language models.<n>It combines a token-equal AR-and-diffusion objective, hardware-aware kernels, and unified inference, enabling one checkpoint to support both AR-style verified decoding and diffusion-style parallel denoising.<n>Our results suggest practical dLLMs are limited not only by decoding algorithms, but also by transfer data quality and the training inefficiency of current block-diffusion objectives.
  arXiv  Detail & Related papers  (2026-06-01T06:58:15Z)
• GLM-OCR Technical Report [65.42028025507491]
  GLM-OCR is an efficient compact model designed for real-world document understanding.<n>It combines a CogViT visual encoder with a GLM language decoder, achieving a strong balance between computational efficiency and recognition performance.<n>Extensive evaluations on public benchmarks and industrial scenarios show that GLM-OCR achieves competitive or state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-03-11T15:55:47Z)
• From Completion to Editing: Unlocking Context-Aware Code Infilling via Search-and-Replace Instruction Tuning [81.97788535387286]
  We propose a framework that internalizes the agentic verification-and-editing mechanism into a unified, single-pass inference process.<n>With minimal data, SRI-Coder enables Chat models to surpass the completion performance of their Base counterparts.<n>Unlike FIM-style tuning, SRI preserves general coding competencies and maintains inference latency comparable to standard FIM.
  arXiv  Detail & Related papers  (2026-01-19T20:33:53Z)
• PEFA-AI: Advancing Open-source LLMs for RTL generation using Progressive Error Feedback Agentic-AI [5.455262834289454]
  We present an agentic flow consisting of multiple agents that collaboratively complete the task of Register Transfer Level (RTL) generation without human intervention.<n>A key feature of the proposed flow is the progressive error feedback system of agents (PEFA), a self-correcting mechanism.<n>To validate this adaptive approach to code generation, benchmarking is performed using two opensource natural language-to-RTL datasets.
  arXiv  Detail & Related papers  (2025-11-06T00:19:47Z)
• AdaptiveK Sparse Autoencoders: Dynamic Sparsity Allocation for Interpretable LLM Representations [28.447024168930984]
  We propose AdaptiveK SAE (Adaptive Top K Sparse Autoencoders), a novel framework that dynamically adjusts sparsity levels based on the semantic complexity of each input.<n>We show that this complexity-driven adaptation significantly outperforms fixed-sparsity approaches on reconstruction fidelity, explained variance, cosine similarity and interpretability metrics.
  arXiv  Detail & Related papers  (2025-08-24T12:00:41Z)
• Large-Scale Model Enabled Semantic Communication Based on Robust Knowledge Distillation [53.16213723669751]
  Large-scale models (LSMs) can be an effective framework for semantic representation and understanding.<n>However, their direct deployment is often hindered by high computational complexity and resource requirements.<n>This paper proposes a novel knowledge distillation based semantic communication framework.
  arXiv  Detail & Related papers  (2025-08-04T07:47:18Z)
• DecoRTL: A Run-time Decoding Framework for RTL Code Generation with LLMs [0.0]
  We show that large language models (LLMs) exhibit low confidence in regions of structural ambiguity or semantic complexity.<n>We introduce DecoRTL, a novel run-time decoding strategy, that is both syntax-aware and contrastive for RTL code generation.<n>Our approach operates entirely at inference time without requiring any additional model fine-tuning.
  arXiv  Detail & Related papers  (2025-07-03T01:17:44Z)
• Boosting CTC-Based ASR Using LLM-Based Intermediate Loss Regularization [5.439020425819001]
  We propose a novel auxiliary loss framework called Language-Aware Intermediate Loss (LAIL) to enhance CTC-based automatic speech recognition systems.<n>LAIL maps outputs to the embedding space of large language models (LLMs) and computes a causal language modeling loss during training.<n>We demonstrate significant improvements in Word Error Rate (WER) on the LibriSpeech, TEDLIUM2, and WSJ corpora, achieving state-of-the-art performance for CTC-based ASR with minimal computational overhead.
  arXiv  Detail & Related papers  (2025-06-28T10:59:42Z)
• Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding [51.711605076319216]
  Diffusion-based large language models (Diffusion LLMs) have shown promise for non-autoregressive text generation with parallel decoding capabilities.<n>We introduce a novel block-wise approximate KV Cache mechanism tailored for bidirectional diffusion models, enabling cache reuse with negligible performance drop.<n>We propose a confidence-aware parallel decoding strategy that selectively decodes tokens exceeding a confidence threshold, mitigating dependency violations and maintaining generation quality.
  arXiv  Detail & Related papers  (2025-05-28T17:39:15Z)
• Large Language Model-Powered Agent for C to Rust Code Translation [2.182572303351317]
  A modern system programming language, Rust, has emerged as a memory-safe alternative to the C programming language.<n>Applying the agentic capability for the C-to-Rust translation introduces distinct challenges.<n>Unlike math or commonsense QA, the intermediate steps required for C-to-Rust are not well-defined.<n>We propose a novel intermediate step, the Virtual Fuzzing-based equivalence Test (VFT), and an agentic planning framework, the LLM-powered Agent for C-to-Rust code translation (LAC2R)
  arXiv  Detail & Related papers  (2025-05-21T01:26:23Z)
• Exploiting Mixture-of-Experts Redundancy Unlocks Multimodal Generative Abilities [69.26544016976396]
  We exploit the redundancy within Mixture-of-Experts (MoEs) as a source of additional capacity for learning a new modality. We preserve the original language generation capabilities by applying low-rank adaptation exclusively to the tokens of the new modality.
  arXiv  Detail & Related papers  (2025-03-28T15:21:24Z)
• ADEM-VL: Adaptive and Embedded Fusion for Efficient Vision-Language Tuning [38.26304604660713]
  ADEM-VL is an efficient vision-language method that tunes models based on pretrained large language models. Our framework surpasses existing methods by an average accuracy of 0.77% on ScienceQA dataset.
  arXiv  Detail & Related papers  (2024-10-23T11:31:06Z)
• EMMA: Efficient Visual Alignment in Multi-Modal LLMs [56.03417732498859]
  EMMA is a lightweight cross-modality module designed to efficiently fuse visual and textual encodings. EMMA boosts performance across multiple tasks by up to 9.3% while significantly improving robustness against hallucinations.
  arXiv  Detail & Related papers  (2024-10-02T23:00:31Z)
• RGD: Multi-LLM Based Agent Debugger via Refinement and Generation Guidance [0.6062751776009752]
  Large Language Models (LLMs) have shown incredible potential in code generation tasks. LLMs can generate code based on task descriptions, but accuracy remains limited. We introduce a novel architecture of LLM-based agents for code generation and automatic debug: Refinement and Guidance debugger (RGD) RGD decomposes the code generation task into multiple steps, ensuring a clearer workflow and enabling iterative code refinement based on self-reflection and feedback.
  arXiv  Detail & Related papers  (2024-10-02T05:07:02Z)
• 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)
• Towards interfacing large language models with ASR systems using confidence measures and prompting [54.39667883394458]
  This work investigates post-hoc correction of ASR transcripts with large language models (LLMs) To avoid introducing errors into likely accurate transcripts, we propose a range of confidence-based filtering methods. Our results indicate that this can improve the performance of less competitive ASR systems.
  arXiv  Detail & Related papers  (2024-07-31T08:00:41Z)
• Exploring the Role of Large Language Models in Prompt Encoding for Diffusion Models [42.891427362223176]
  Large language models (LLMs) based on decoder-only transformers have demonstrated superior text understanding capabilities. We propose a novel framework to fully harness the capabilities of LLMs. We further design an LLM-Infused Diffusion Transformer (LI-DiT) based on the framework.
  arXiv  Detail & Related papers  (2024-06-17T17:59:43Z)
• Generation Meets Verification: Accelerating Large Language Model Inference with Smart Parallel Auto-Correct Decoding [11.832919020149891]
  This research aims to accelerate the inference speed of large language models (LLMs) with billions of parameters. We propose textbfSmart textbfParallel textbfAuto-textbfCorrect dtextbfEcoding (SPACE)
  arXiv  Detail & Related papers  (2024-02-19T03:39:10Z)
• CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular Fusion [58.15403987979496]
  CREMA is a generalizable, highly efficient, and modular modality-fusion framework for video reasoning. We propose a novel progressive multimodal fusion design supported by a lightweight fusion module and modality-sequential training strategy. We validate our method on 7 video-language reasoning tasks assisted by diverse modalities, including VideoQA and Video-Audio/3D/Touch/Thermal QA.
  arXiv  Detail & Related papers  (2024-02-08T18:27:22Z)
• It's Never Too Late: Fusing Acoustic Information into Large Language Models for Automatic Speech Recognition [70.77292069313154]
  Large language models (LLMs) can be successfully used for generative error correction (GER) on top of the automatic speech recognition (ASR) output. In this work, we aim to overcome such a limitation by infusing acoustic information before generating the predicted transcription through a novel late fusion solution termed Uncertainty-Aware Dynamic Fusion (UADF)
  arXiv  Detail & Related papers  (2024-02-08T07:21:45Z)
• Computation and Parameter Efficient Multi-Modal Fusion Transformer for Cued Speech Recognition [48.84506301960988]
  Cued Speech (CS) is a pure visual coding method used by hearing-impaired people. automatic CS recognition (ACSR) seeks to transcribe visual cues of speech into text.
  arXiv  Detail & Related papers  (2024-01-31T05:20:29Z)
• LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models [56.25156596019168]
  This paper introduces the LMRL-Gym benchmark for evaluating multi-turn RL for large language models (LLMs) Our benchmark consists of 8 different language tasks, which require multiple rounds of language interaction and cover a range of tasks in open-ended dialogue and text games.
  arXiv  Detail & Related papers  (2023-11-30T03:59:31Z)
• FLIP: Fine-grained Alignment between ID-based Models and Pretrained Language Models for CTR Prediction [49.510163437116645]
  Click-through rate (CTR) prediction plays as a core function module in personalized online services. Traditional ID-based models for CTR prediction take as inputs the one-hot encoded ID features of tabular modality. Pretrained Language Models(PLMs) has given rise to another paradigm, which takes as inputs the sentences of textual modality. We propose to conduct Fine-grained feature-level ALignment between ID-based Models and Pretrained Language Models(FLIP) for CTR prediction.
  arXiv  Detail & Related papers  (2023-10-30T11:25:03Z)
• Large Language Models can Contrastively Refine their Generation for Better Sentence Representation Learning [57.74233319453229]
  Large language models (LLMs) have emerged as a groundbreaking technology and their unparalleled text generation capabilities have sparked interest in their application to the fundamental sentence representation learning task. We propose MultiCSR, a multi-level contrastive sentence representation learning framework that decomposes the process of prompting LLMs to generate a corpus. Our experiments reveal that MultiCSR enables a less advanced LLM to surpass the performance of ChatGPT, while applying it to ChatGPT achieves better state-of-the-art results.
  arXiv  Detail & Related papers  (2023-10-17T03:21:43Z)

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.