Un-Doubling Diffusion: LLM-guided Disambiguation of Homonym Duplication

• URL: http://arxiv.org/abs/2509.21262v2
• Date: Sun, 28 Sep 2025 07:41:18 GMT
• Title: Un-Doubling Diffusion: LLM-guided Disambiguation of Homonym Duplication
• Authors: Evgeny Kaskov, Elizaveta Petrova, Petr Surovtsev, Anna Kostikova, Ilya Mistiurin, Alexander Kapitanov, Alexander Nagaev,
• Abstract summary: Homonyms are words with identical spelling but distinct meanings.<n> diffusion models may generate multiple senses of the word simultaneously, which is known as homonym duplication.<n>We introduce a method for measuring duplication rates and conduct evaluations of different diffusion models.
• Score: 65.67239638031617
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Homonyms are words with identical spelling but distinct meanings, which pose challenges for many generative models. When a homonym appears in a prompt, diffusion models may generate multiple senses of the word simultaneously, which is known as homonym duplication. This issue is further complicated by an Anglocentric bias, which includes an additional translation step before the text-to-image model pipeline. As a result, even words that are not homonymous in the original language may become homonyms and lose their meaning after translation into English. In this paper, we introduce a method for measuring duplication rates and conduct evaluations of different diffusion models using both automatic evaluation utilizing Vision-Language Models (VLM) and human evaluation. Additionally, we investigate methods to mitigate the homonym duplication problem through prompt expansion, demonstrating that this approach also effectively reduces duplication related to Anglocentric bias. The code for the automatic evaluation pipeline is publicly available.

Related papers

• Generalized Interpolating Discrete Diffusion [65.74168524007484]
  Masked diffusion is a popular choice due to its simplicity and effectiveness.<n>We generalize a new family of general interpolating discrete diffusion (GIDD) which offers greater flexibility in the design of the noising processes.<n>Exploiting GIDD's flexibility, we explore a hybrid approach combining masking and uniform noise, leading to improved sample quality.
  arXiv  Detail & Related papers  (2025-03-06T14:30:55Z)
• Cluster-Aware Similarity Diffusion for Instance Retrieval [64.40171728912702]
  Diffusion-based re-ranking is a common method used for retrieving instances by performing similarity propagation in a nearest neighbor graph.<n>We propose a novel Cluster-Aware Similarity (CAS) diffusion for instance retrieval.
  arXiv  Detail & Related papers  (2024-06-04T14:19:50Z)
• PLANNER: Generating Diversified Paragraph via Latent Language Diffusion Model [37.2192243883707]
  We propose PLANNER, a model that combines latent semantic diffusion with autoregressive generation to generate fluent text. Results on semantic generation, text completion and summarization show its effectiveness in generating high-quality long-form text.
  arXiv  Detail & Related papers  (2023-06-05T01:36:39Z)
• A Tale of Two Laws of Semantic Change: Predicting Synonym Changes with Distributional Semantic Models [1.856334276134661]
  There are two competing, apparently opposite hypotheses in the historical linguistic literature regarding how synonymous words evolve. We take a first step toward detecting whether Law of Differentiation (LD) or Law of Parallel Change (LPC) operates for given word pairs. We then propose various computational approaches to the problem using Distributional Semantic Models and grounded in recent literature on Lexical Semantic Change detection.
  arXiv  Detail & Related papers  (2023-05-30T15:50:29Z)
• Towards Unsupervised Recognition of Token-level Semantic Differences in Related Documents [61.63208012250885]
  We formulate recognizing semantic differences as a token-level regression task. We study three unsupervised approaches that rely on a masked language model. Our results show that an approach based on word alignment and sentence-level contrastive learning has a robust correlation to gold labels.
  arXiv  Detail & Related papers  (2023-05-22T17:58:04Z)
• Patterns of Lexical Ambiguity in Contextualised Language Models [9.747449805791092]
  We introduce an extended, human-annotated dataset of graded word sense similarity and co-predication. Both types of human judgements indicate that the similarity of polysemic interpretations falls in a continuum between identity of meaning and homonymy. Our dataset appears to capture a substantial part of the complexity of lexical ambiguity, and can provide a realistic test bed for contextualised embeddings.
  arXiv  Detail & Related papers  (2021-09-27T13:11:44Z)
• Studying word order through iterative shuffling [14.530986799844873]
  We show that word order encodes meaning essential to performing NLP benchmark tasks. We use IBIS, a novel, efficient procedure that finds the ordering of a bag of words having the highest likelihood under a fixed language model. We discuss how shuffling inference procedures such as IBIS can benefit language modeling and constrained generation.
  arXiv  Detail & Related papers  (2021-09-10T13:27:06Z)
• On Sampling-Based Training Criteria for Neural Language Modeling [97.35284042981675]
  We consider Monte Carlo sampling, importance sampling, a novel method we call compensated partial summation, and noise contrastive estimation. We show that all these sampling methods can perform equally well, as long as we correct for the intended class posterior probabilities. Experimental results in language modeling and automatic speech recognition on Switchboard and LibriSpeech support our claim.
  arXiv  Detail & Related papers  (2021-04-21T12:55:52Z)
• Novel Aficionados and Doppelg\"angers: a referential task for semantic representations of individual entities [0.0]
  We show that the semantic distinction between proper names and common nouns is reflected in their linguistic distributions. The results indicate that the distributional representations of different individual entities are less clearly distinguishable from each other than those of common nouns.
  arXiv  Detail & Related papers  (2021-04-20T22:24:19Z)
• Detecting Word Sense Disambiguation Biases in Machine Translation for Model-Agnostic Adversarial Attacks [84.61578555312288]
  We introduce a method for the prediction of disambiguation errors based on statistical data properties. We develop a simple adversarial attack strategy that minimally perturbs sentences in order to elicit disambiguation errors. Our findings indicate that disambiguation robustness varies substantially between domains and that different models trained on the same data are vulnerable to different attacks.
  arXiv  Detail & Related papers  (2020-11-03T17:01:44Z)
• Investigating Cross-Linguistic Adjective Ordering Tendencies with a Latent-Variable Model [66.84264870118723]
  We present the first purely corpus-driven model of multi-lingual adjective ordering in the form of a latent-variable model. We provide strong converging evidence for the existence of universal, cross-linguistic, hierarchical adjective ordering tendencies.
  arXiv  Detail & Related papers  (2020-10-09T18:27:55Z)
• Paraphrase Generation as Zero-Shot Multilingual Translation: Disentangling Semantic Similarity from Lexical and Syntactic Diversity [11.564158965143418]
  We introduce a simple paraphrase generation algorithm which discourages the production of n-grams that are present in the input. Our approach enables paraphrase generation in many languages from a single multilingual NMT model.
  arXiv  Detail & Related papers  (2020-08-11T18:05:34Z)

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.