Learning by Surprise: Surplexity for Mitigating Model Collapse in Generative AI

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Gambetta, Daniele, Gezici, Gizem, Giannotti, Fosca, Pedreschi, Dino, Knott, Alistair, Pappalardo, Luca
Format:	Preprint
Published:	2024
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

Hybrid Retrieval for Hallucination Mitigation in Large Language Models: A Comparative Analysis
by: Mala, Chandana Sree, et al.
Published: (2025)

Perspectives in Play: A Multi-Perspective Approach for More Inclusive NLP Systems
by: Muscato, Benedetta, et al.
Published: (2025)

Embracing Diversity: A Multi-Perspective Approach with Soft Labels
by: Muscato, Benedetta, et al.
Published: (2025)

A survey on the impacts of recommender systems on users, items, and human-AI ecosystems
by: Pappalardo, Luca, et al.
Published: (2024)

AI, Meet Human: Learning Paradigms for Hybrid Decision Making Systems
by: Punzi, Clara, et al.
Published: (2024)

The Diversity Paradox revisited: Systemic Effects of Feedback Loops in Recommender Systems
by: Barlacchi, Gabriele, et al.
Published: (2026)

Bridging the Gap: In-Context Learning for Modeling Human Disagreement
by: Muscato, Benedetta, et al.
Published: (2025)

Multi-Perspective Stance Detection
by: Muscato, Benedetta, et al.
Published: (2024)

Disagreeing Rationales: Rethinking Classification and Explainability Evaluation in Hate Speech Detection
by: Muscato, Benedetta, et al.
Published: (2026)

Interpretable and Fair Mechanisms for Abstaining Classifiers
by: Lenders, Daphne, et al.
Published: (2025)

Human-AI Coevolution
by: Pedreschi, Dino, et al.
Published: (2023)

Boosting Synthetic Data Generation with Effective Nonlinear Causal Discovery
by: Cinquini, Martina, et al.
Published: (2023)

Comparing Explanations is Not Enough, Explain the Change: New Standards are Needed to Explain Behavioral Shifts in Large Language Models
by: Ciaperoni, Martino, et al.
Published: (2026)

Explanations Go Linear: Post-hoc Explainability for Tabular Data with Interpretable Meta-Encoding
by: Piaggesi, Simone, et al.
Published: (2025)

Spectral Characterization and Mitigation of Sequential Knowledge Editing Collapse
by: Zhang, Chi, et al.
Published: (2026)

Confabulation: The Surprising Value of Large Language Model Hallucinations
by: Sui, Peiqi, et al.
Published: (2024)

Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversity
by: Zhang, Jiayi, et al.
Published: (2025)

Mitigation of Gender and Ethnicity Bias in AI-Generated Stories through Model Explanations
by: Dimgba, Martha O., et al.
Published: (2025)

Surprising Efficacy of Fine-Tuned Transformers for Fact-Checking over Larger Language Models
by: Setty, Vinay
Published: (2024)

Code-Based English Models Surprising Performance on Chinese QA Pair Extraction Task
by: Zheng, Linghan, et al.
Published: (2024)

Generating Reports or Repeating Templates? Measuring and Mitigating Template Collapse in 3D CT Report Generation
by: Maye-Lasserre, Tom, et al.
Published: (2026)

Collapse of Self-trained Language Models
by: Herel, David, et al.
Published: (2024)

Understanding the Collapse of LLMs in Model Editing
by: Yang, Wanli, et al.
Published: (2024)

The Surprising Effectiveness of Test-Time Training for Few-Shot Learning
by: Akyürek, Ekin, et al.
Published: (2024)

Does Knowledge Localization Hold True? Surprising Differences Between Entity and Relation Perspectives in Language Models
by: Wei, Yifan, et al.
Published: (2024)

Whispering Experts: Neural Interventions for Toxicity Mitigation in Language Models
by: Suau, Xavier, et al.
Published: (2024)

Mitigating Clickbait: An Approach to Spoiler Generation Using Multitask Learning
by: Pal, Sayantan, et al.
Published: (2024)

SuRe: Surprise-Driven Prioritised Replay for Continual LLM Learning
by: Hazard, Hugo, et al.
Published: (2025)

Detecting Mode Collapse in Language Models via Narration
by: Hamilton, Sil
Published: (2024)

Autonomous Structural Memory Manipulation for Large Language Models Using Hierarchical Embedding Augmentation
by: Yotheringhay, Derek, et al.
Published: (2025)

Extending Minimal Pairs with Ordinal Surprisal Curves and Entropy Across Applied Domains
by: Katz, Andrew
Published: (2026)

Rebuilding ROME : Resolving Model Collapse during Sequential Model Editing
by: Gupta, Akshat, et al.
Published: (2024)

C3AI: Crafting and Evaluating Constitutions for Constitutional AI
by: Kyrychenko, Yara, et al.
Published: (2025)

The Future of Learning in the Age of Generative AI: Automated Question Generation and Assessment with Large Language Models
by: Maity, Subhankar, et al.
Published: (2024)

Do LLMs Judge Distantly Supervised Named Entity Labels Well? Constructing the JudgeWEL Dataset
by: Plum, Alistair, et al.
Published: (2026)

REFINE-LM: Mitigating Language Model Stereotypes via Reinforcement Learning
by: Qureshi, Rameez, et al.
Published: (2024)

Understanding and Mitigating Risks of Generative AI in Financial Services
by: Gehrmann, Sebastian, et al.
Published: (2025)

ConsistencyAI: A Benchmark to Assess LLMs' Factual Consistency When Responding to Different Demographic Groups
by: Banyas, Peter, et al.
Published: (2025)

The Urban Impact of AI: Modeling Feedback Loops in Next-Venue Recommendation
by: Mauro, Giovanni, et al.
Published: (2025)

The Pitfalls of Publishing in the Age of LLMs: Strange and Surprising Adventures with a High-Impact NLP Journal
by: Verma, Rakesh M., et al.
Published: (2024)