Semantic Reasoning Denoising: Correcting Language Model Reasoning with Semantic Operators

• URL: http://arxiv.org/abs/2608.22090v1
• Date: Sat, 22 Aug 2026 19:43:46 GMT
• Title: Semantic Reasoning Denoising: Correcting Language Model Reasoning with Semantic Operators
• Abstract summary: Large language models can produce fluent reasoning traces whose local semantic errors propagate to an incorrect conclusion.<n>We present Semantic Reasoning Denoising (SRD), an operatorized Markov denoising method for natural-language reasoning trajectories.<n>SRD represents semantic noise with executable error operators that describe the error type, its location, and the corrupted and repaired propositions.
• Score: 0.2538209532048867
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models can produce fluent reasoning traces whose local semantic errors propagate to an incorrect conclusion, while unconstrained self-correction may preserve, amplify, or introduce errors. Existing diffusion language models provide iterative refinement, but usually define noise as token masking or replacement rather than as errors in the reasoning process. We present Semantic Reasoning Denoising (SRD), an operatorized Markov denoising method for natural-language reasoning trajectories. SRD represents semantic noise with executable error operators that describe the error type, its location, and the corrupted and repaired propositions. Composing these operators constructs progressively noisier states. During training, the model learns to identify the semantic noise active in the current trajectory and to reconstruct the paired adjacent lower-noise state. During inference, noise-level-aware denoising repeatedly predicts an inverse operator and checks whether it is applicable, so each executed update makes a localized move toward a stable trajectory. Across six in-domain benchmarks spanning mathematics, code, knowledge, and commonsense, SRD improves the strongest same backbone baseline by 3.2 points on average. On seven cross-dataset transfer targets, it remains competitive with Llama-3-8B-Instruct and improves the strongest Qwen3-8B baseline average by 2.9 points. Analyses of noise sources, objectives, and denoising depth further show that structured semantic-noise prediction and iterative operator execution are central to the improvement.

Related papers

• When Is Noise Response Universal? Tokenization as the Hidden Variable in Language Models [3.6243102296545846]
  We study the degradation rate across neural models, both sentence embeddings and decoder-only LLMs.<n>We find that under word-level noise, models with very different architectures decline along nearly the same curve, while under character-level noise they separate.<n>This finding and its underlying mechanism provide a practical means to predict a model's robustness to noise without any noisy evaluation.
  arXiv  Detail & Related papers  (2026-08-26T18:51:51Z)
• DACA-GRPO: Denoising-Aware Credit Assignment for Reinforcement Learning in Diffusion Language Models [9.199240801552302]
  We propose Denoising-Aware Credit Assignment for GRPO (DACA-GRPO), a plug-and-play enhancement for any GRPO-style trainer.<n>DACA-GRPO achieves consistent improvements across seven benchmarks spanning mathematical reasoning, code generation, constraint satisfaction, and constrained generation.
  arXiv  Detail & Related papers  (2026-05-08T01:02:31Z)
• Adaptive Guidance for Retrieval-Augmented Masked Diffusion Models [60.25003813232697]
  We propose Adaptive Retrieval-Augmented Masked Diffusion (ARAM) as a training-free adaptive guidance framework for Masked Diffusion Models (MDMs)<n>ARAM calibrates the guidance scale during denoising according to the Signal-to-Noise Ratio (SNR) of the distributional shift induced by retrieved context.<n>Experiments on multiple knowledge-intensive QA benchmarks show that ARAM improves overall QA performance over competitive RAG baselines.
  arXiv  Detail & Related papers  (2026-03-18T12:54:50Z)
• Incorporating Error Level Noise Embedding for Improving LLM-Assisted Robustness in Persian Speech Recognition [1.3607388598209322]
  This study presents a robust noise-sensitive ASR error correction framework that combines multiple hypotheses and noise-aware modeling.<n>Using noisy Persian speech, we generate 5-best hypotheses from a modified Whisper-large decoder.<n> Experimental results demonstrate that the ELN-conditioned model achieves substantial reductions in Word Error Rate (WER)
  arXiv  Detail & Related papers  (2025-12-19T05:26:50Z)
• From Denoising to Refining: A Corrective Framework for Vision-Language Diffusion Model [72.73512218682187]
  We introduce ReDiff, a refining-enhanced diffusion framework that teaches the model to identify and correct its own errors.<n>Our approach features a two-stage training process: first, we instill a foundational revision capability by training the model to revise synthetic errors; second, we implement a novel online self-correction loop.<n>This mistake-driven learning endows the model with the crucial ability to revisit and refine its already generated output, effectively breaking the error cascade.
  arXiv  Detail & Related papers  (2025-10-22T06:58:55Z)
• InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationales [14.655518998487237]
  We propose InstructRAG, where LMs explicitly learn the denoising process through self-synthesized rationales.<n>InstructRAG requires no additional supervision, allows for easier verification of the predicted answers.<n>Experiments show InstructRAG consistently outperforms existing RAG methods in both training-free and trainable scenarios.
  arXiv  Detail & Related papers  (2024-06-19T15:25:29Z)
• Large Language Models are Efficient Learners of Noise-Robust Speech Recognition [65.95847272465124]
  Recent advances in large language models (LLMs) have promoted generative error correction (GER) for automatic speech recognition (ASR) In this work, we extend the benchmark to noisy conditions and investigate if we can teach LLMs to perform denoising for GER. Experiments on various latest LLMs demonstrate our approach achieves a new breakthrough with up to 53.9% correction improvement in terms of word error rate.
  arXiv  Detail & Related papers  (2024-01-19T01:29:27Z)
• HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models [81.56455625624041]
  We introduce the first open-source benchmark to utilize external large language models (LLMs) for ASR error correction. The proposed benchmark contains a novel dataset, HyPoradise (HP), encompassing more than 334,000 pairs of N-best hypotheses. LLMs with reasonable prompt and its generative capability can even correct those tokens that are missing in N-best list.
  arXiv  Detail & Related papers  (2023-09-27T14:44:10Z)
• Instance Regularization for Discriminative Language Model Pre-training [108.41891836796366]
  This work proposes to estimate the complexity of restoring the original sentences from corrupted ones in language model pre-training. Experimental results on natural language understanding and reading comprehension benchmarks show that our approach improves pre-training efficiency, effectiveness, and robustness.
  arXiv  Detail & Related papers  (2022-10-11T14:16:37Z)
• Robustification of Multilingual Language Models to Real-world Noise with Robust Contrastive Pretraining [14.087882550564169]
  We assess the robustness of neural models on noisy data and suggest improvements are limited to the English language. To benchmark the performance of pretrained multilingual models, we construct noisy datasets covering five languages and four NLP tasks. We propose Robust Contrastive Pretraining (RCP) to boost the zero-shot cross-lingual robustness of multilingual pretrained models.
  arXiv  Detail & Related papers  (2022-10-10T15:40:43Z)
• Avoiding Inference Heuristics in Few-shot Prompt-based Finetuning [57.4036085386653]
  We show that prompt-based models for sentence pair classification tasks still suffer from a common pitfall of adopting inferences based on lexical overlap. We then show that adding a regularization that preserves pretraining weights is effective in mitigating this destructive tendency of few-shot finetuning.
  arXiv  Detail & Related papers  (2021-09-09T10:10:29Z)

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.