Cover Image

From Noise to Signal: When Outliers Seed New Topics

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zve, Evangelia, Bourgne, Gauvain, Icard, Benjamin, Ganascia, Jean-Gabriel
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

From Outliers to Topics in Language Models: Anticipating Trends in News Corpora
by: Zve, Evangelia, et al.
Published: (2025)

Embedding Style Beyond Topics: Analyzing Dispersion Effects Across Different Language Models
by: Icard, Benjamin, et al.
Published: (2025)

Measuring Embedding Sensitivity to Authorial Style in French: Comparing Literary Texts with Language Model Rewritings
by: Icard, Benjamin, et al.
Published: (2026)

Reliable News or Propagandist News? A Neurosymbolic Model Using Genre, Topic, and Persuasion Techniques to Improve Robustness in Classification
by: Faye, Géraud, et al.
Published: (2026)

An Argumentative Explanation Framework for Generalized Reason Model with Inconsistent Precedents
by: Fungwacharakorn, Wachara, et al.
Published: (2025)

Identifying Narrative Patterns and Outliers in Holocaust Testimonies Using Topic Modeling
by: Ifergan, Maxim, et al.
Published: (2024)

How Causal Abstraction Underpins Computational Explanation
by: Geiger, Atticus, et al.
Published: (2025)

HYBRINFOX at CheckThat! 2024 -- Task 1: Enhancing Language Models with Structured Information for Check-Worthiness Estimation
by: Faye, Géraud, et al.
Published: (2024)

HYBRINFOX at CheckThat! 2024 -- Task 2: Enriching BERT Models with the Expert System VAGO for Subjectivity Detection
by: Casanova, Morgane, et al.
Published: (2024)

An action language-based formalisation of an abstract argumentation framework
by: Munro, Yann, et al.
Published: (2024)

When Numbers Tell Half the Story: Human-Metric Alignment in Topic Model Evaluation
by: Prouteau, Thibault, et al.
Published: (2026)

Bucketing the Good Apples: A Method for Diagnosing and Improving Causal Abstraction
by: Puyin, Li, et al.
Published: (2026)

From Noise to Signal to Selbstzweck: Reframing Human Label Variation in the Era of Post-training in NLP
by: Xu, Shanshan, et al.
Published: (2025)

Personalized Topic Selection Model for Topic-Grounded Dialogue
by: Fan, Shixuan, et al.
Published: (2024)

Text-as-Signal: Quantitative Semantic Scoring with Embeddings, Logprobs, and Noise Reduction
by: Moreira, Hugo
Published: (2026)

Improving Neural Topic Modeling with Semantically-Grounded Soft Label Distributions
by: Li, Raymond, et al.
Published: (2026)

Outliers Dimensions that Disrupt Transformers Are Driven by Frequency
by: Puccetti, Giovanni, et al.
Published: (2022)

Outlier Dimensions Encode Task-Specific Knowledge
by: Rudman, William, et al.
Published: (2023)

Is It a Free Lunch for Removing Outliers during Pretraining?
by: Liao, Baohao, et al.
Published: (2024)

Internal Causal Mechanisms Robustly Predict Language Model Out-of-Distribution Behaviors
by: Huang, Jing, et al.
Published: (2025)

Rethinking the Outlier Distribution in Large Language Models: An In-depth Study
by: Raman, Rahul, et al.
Published: (2025)

CzechTopic: A Benchmark for Zero-Shot Topic Localization in Historical Czech Documents
by: Kostelník, Martin, et al.
Published: (2026)

TopicENA: Enabling Epistemic Network Analysis at Scale through Automated Topic-Based Coding
by: Lu, Owen H. T., et al.
Published: (2026)

Advancing Topic Segmentation and Outline Generation in Chinese Texts: The Paragraph-level Topic Representation, Corpus, and Benchmark
by: Jiang, Feng, et al.
Published: (2023)

TopicImpact: Improving Customer Feedback Analysis with Opinion Units for Topic Modeling and Star-Rating Prediction
by: Häglund, Emil, et al.
Published: (2025)

AlbNews: A Corpus of Headlines for Topic Modeling in Albanian
by: Çano, Erion, et al.
Published: (2024)

Anti-Length Shift: Dynamic Outlier Truncation for Training Efficient Reasoning Models
by: Wu, Wei, et al.
Published: (2026)

Belief in the Machine: Investigating Epistemological Blind Spots of Language Models
by: Suzgun, Mirac, et al.
Published: (2024)

SeedPrints: Fingerprints Can Even Tell Which Seed Your Large Language Model Was Trained From
by: Tong, Yao, et al.
Published: (2025)

Systematic Outliers in Large Language Models
by: An, Yongqi, et al.
Published: (2025)

Exposing propaganda: an analysis of stylistic cues comparing human annotations and machine classification
by: Faye, Géraud, et al.
Published: (2024)

BATQuant: Outlier-resilient MXFP4 Quantization via Learnable Block-wise Optimization
by: Li, Ji-Fu, et al.
Published: (2026)

Topic-Conversation Relevance (TCR) Dataset and Benchmarks
by: Fan, Yaran, et al.
Published: (2024)

Topic Segmentation Using Generative Language Models
by: Mackenzie, Pierre, et al.
Published: (2025)

TopicProphet: Prophesies on Temporal Topic Trends and Stocks
by: Kim, Olivia
Published: (2025)

Uncertainty-Aware Gradient Signal-to-Noise Data Selection for Instruction Tuning
by: Yuan, Zhihang, et al.
Published: (2026)

Signal in the Noise: Polysemantic Interference Transfers and Predicts Cross-Model Influence
by: Gong, Bofan, et al.
Published: (2025)

When Perplexity Lies: Generation-Focused Distillation of Hybrid Sequence Models
by: Kostelec, Juan Gabriel, et al.
Published: (2026)

Persistent Homology of Topic Networks for the Prediction of Reader Curiosity
by: Hopp, Manuel D. S., et al.
Published: (2025)

Topic-to-essay generation with knowledge-based content selection
by: Wang, Jieyong, et al.
Published: (2024)