Does Linguistic Structure Enrichment Enhance Coherence Assessment? Not With Current Architectures

• URL: http://arxiv.org/abs/2609.10893v1
• Date: Wed, 09 Sep 2026 22:53:50 GMT
• Title: Does Linguistic Structure Enrichment Enhance Coherence Assessment? Not With Current Architectures
• Abstract summary: We investigate whether enriching text with syntactic and rhetorical information can improve incoherence prediction.<n>Experiments and analysis show that plain texts achieved higher accuracy because the added information was structurally and syntactically incompatible with the language model's architecture.
• Score: 1.756239703835073
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Recent advances in large language models have transformed human-computer interaction. Despite their fluency, these models often produce texts that are grammatically correct but semantically incoherent, containing contradictions or disruptions in logical flow. This work investigates whether enriching text with syntactic and rhetorical information can improve incoherence prediction. Our experiments and analysis show that plain texts achieved higher accuracy because the added information was structurally and syntactically incompatible with the language model's architecture. Additionally, to demonstrate the practical importance of coherence assessment, we performed zero-shot experiments on a Brazilian disinformation dataset, suggesting that textual coherence can serve as a proxy for detecting misleading content. Code and models are available at https://github.com/ittozzamV/cohereclassifier.

Related papers

• Rethinking the Role of Text Complexity in Language Model Pretraining [0.19258299315493077]
  We simplify human-written texts using a large language model, pretrain causal models from scratch on original vs. simplified data, and evaluate them in fine-tuning and zero-shot setups.<n>We find that perplexity is sensitive to the interaction between model capacity and text complexity--smaller models degrade far less on simpler texts--while text complexity has little impact on fine-tuning evaluations.
  arXiv  Detail & Related papers  (2025-09-20T06:33:01Z)
• Learning Interpretable Representations Leads to Semantically Faithful EEG-to-Text Generation [52.51005875755718]
  We focus on EEG-to-text decoding and address its hallucination issue through the lens of posterior collapse.<n>Acknowledging the underlying mismatch in information capacity between EEG and text, we reframe the decoding task as semantic summarization of core meanings.<n>Experiments on the public ZuCo dataset demonstrate that GLIM consistently generates fluent, EEG-grounded sentences.
  arXiv  Detail & Related papers  (2025-05-21T05:29:55Z)
• Empirical Evaluation of Embedding Models in the Context of Text Classification in Document Review in Construction Delay Disputes [6.076874513889027]
  Text embeddings are numerical representations of text data, where words, phrases, or entire documents are converted into vectors of real numbers.<n>This paper presents our work in evaluating different embeddings through a comprehensive comparative analysis of four distinct models.<n>We employ both K-Nearest Neighbors (KNN) and Logistic Regression (LR) to perform binary classification tasks, specifically determining whether a text snippet is associated with 'delay' or 'not delay' within a labeled dataset.
  arXiv  Detail & Related papers  (2025-01-16T22:12:11Z)
• Putting Context in Context: the Impact of Discussion Structure on Text Classification [13.15873889847739]
  We propose a series of experiments on a large dataset for stance detection in English. We evaluate the contribution of different types of contextual information. We show that structural information can be highly beneficial to text classification but only under certain circumstances.
  arXiv  Detail & Related papers  (2024-02-05T12:56:22Z)
• How Well Do Text Embedding Models Understand Syntax? [50.440590035493074]
  The ability of text embedding models to generalize across a wide range of syntactic contexts remains under-explored. Our findings reveal that existing text embedding models have not sufficiently addressed these syntactic understanding challenges. We propose strategies to augment the generalization ability of text embedding models in diverse syntactic scenarios.
  arXiv  Detail & Related papers  (2023-11-14T08:51:00Z)
• SenteCon: Leveraging Lexicons to Learn Human-Interpretable Language Representations [51.08119762844217]
  SenteCon is a method for introducing human interpretability in deep language representations. We show that SenteCon provides high-level interpretability at little to no cost to predictive performance on downstream tasks.
  arXiv  Detail & Related papers  (2023-05-24T05:06:28Z)
• Model Criticism for Long-Form Text Generation [113.13900836015122]
  We apply a statistical tool, model criticism in latent space, to evaluate the high-level structure of generated text. We perform experiments on three representative aspects of high-level discourse -- coherence, coreference, and topicality. We find that transformer-based language models are able to capture topical structures but have a harder time maintaining structural coherence or modeling coreference.
  arXiv  Detail & Related papers  (2022-10-16T04:35:58Z)
• The Whole Truth and Nothing But the Truth: Faithful and Controllable Dialogue Response Generation with Dataflow Transduction and Constrained Decoding [65.34601470417967]
  We describe a hybrid architecture for dialogue response generation that combines the strengths of neural language modeling and rule-based generation. Our experiments show that this system outperforms both rule-based and learned approaches in human evaluations of fluency, relevance, and truthfulness.
  arXiv  Detail & Related papers  (2022-09-16T09:00:49Z)
• "Let's Eat Grandma": When Punctuation Matters in Sentence Representation for Sentiment Analysis [13.873803872380229]
  We argue that punctuation could play a significant role in sentiment analysis and propose a novel representation model to improve syntactic and contextual performance. We conduct experiments on publicly available datasets and verify that our model can identify the sentiments more accurately over other state-of-the-art baseline methods.
  arXiv  Detail & Related papers  (2020-12-10T19:07:31Z)
• Neural Deepfake Detection with Factual Structure of Text [78.30080218908849]
  We propose a graph-based model for deepfake detection of text. Our approach represents the factual structure of a given document as an entity graph. Our model can distinguish the difference in the factual structure between machine-generated text and human-written text.
  arXiv  Detail & Related papers  (2020-10-15T02:35:31Z)

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.