Cover Image

Neither Stochastic Parroting nor AGI: LLMs Solve Tasks through Context-Directed Extrapolation from Training Data Priors

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Madabushi, Harish Tayyar, Torgbi, Melissa, Bonial, Claire
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Dancing with Deer: A Constructional Perspective on MWEs in the Era of LLMs
by: Bonial, Claire, et al.
Published: (2025)

Evaluating CxG Generalisation in LLMs via Construction-Based NLI Fine Tuning
by: Mackintosh, Tom, et al.
Published: (2025)

Beyond Memorization: Assessing Semantic Generalization in Large Language Models Using Phrasal Constructions
by: Scivetti, Wesley, et al.
Published: (2025)

Adapting Whisper for Regional Dialects: Enhancing Public Services for Vulnerable Populations in the United Kingdom
by: Torgbi, Melissa, et al.
Published: (2025)

FS-RAG: A Frame Semantics Based Approach for Improved Factual Accuracy in Large Language Models
by: Madabushi, Harish Tayyar
Published: (2024)

The Inherent Limits of Pretrained LLMs: The Unexpected Convergence of Instruction Tuning and In-Context Learning Capabilities
by: Bigoulaeva, Irina, et al.
Published: (2025)

SpeciaLex: A Benchmark for In-Context Specialized Lexicon Learning
by: Imperial, Joseph Marvin, et al.
Published: (2024)

Pre-Trained Language Models Represent Some Geographic Populations Better Than Others
by: Dunn, Jonathan, et al.
Published: (2024)

Scaling Policy Compliance Assessment in Language Models with Policy Reasoning Traces
by: Imperial, Joseph Marvin, et al.
Published: (2025)

Safer Policy Compliance with Dynamic Epistemic Fallback
by: Imperial, Joseph Marvin, et al.
Published: (2026)

Evaluating Large Language Models on Multiword Expressions in Multilingual and Code-Switched Contexts
by: De Leon, Frances Laureano, et al.
Published: (2025)

Code-Mixed Probes Show How Pre-Trained Models Generalise On Code-Switched Text
by: De Leon, Frances A. Laureano, et al.
Published: (2024)

Standardize: Aligning Language Models with Expert-Defined Standards for Content Generation
by: Imperial, Joseph Marvin, et al.
Published: (2024)

Are Emergent Abilities in Large Language Models just In-Context Learning?
by: Lu, Sheng, et al.
Published: (2023)

Fine-Tuning on Diverse Reasoning Chains Drives Within-Inference CoT Refinement in LLMs
by: Puerto, Haritz, et al.
Published: (2024)

Illusion or Algorithm? Investigating Memorization, Emergence, and Symbolic Processing in In-Context Learning
by: Niu, Jingcheng, et al.
Published: (2025)

Standardizing Intelligence: Aligning Generative AI for Regulatory and Operational Compliance
by: Imperial, Joseph Marvin, et al.
Published: (2025)

Neither Valid nor Reliable? Investigating the Use of LLMs as Judges
by: Chehbouni, Khaoula, et al.
Published: (2025)

Word Boundary Information Isn't Useful for Encoder Language Models
by: Gow-Smith, Edward, et al.
Published: (2024)

UniversalCEFR: Enabling Open Multilingual Research on Language Proficiency Assessment
by: Imperial, Joseph Marvin, et al.
Published: (2025)

InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory
by: Xiao, Chaojun, et al.
Published: (2024)

The Parrot Dilemma: Human-Labeled vs. LLM-augmented Data in Classification Tasks
by: Møller, Anders Giovanni, et al.
Published: (2023)

FRIDA to the Rescue! Analyzing Synthetic Data Effectiveness in Object-Based Common Sense Reasoning for Disaster Response
by: Shichman, Mollie, et al.
Published: (2025)

Who Are All The Stochastic Parrots Imitating? They Should Tell Us!
by: Shaier, Sagi, et al.
Published: (2023)

Sensivity of LLMs' Explanations to the Training Randomness:Context, Class & Task Dependencies
by: Loncour, Romain, et al.
Published: (2026)

Neither Consent nor Property: A Policy Lab for Data Law
by: Zhang, Haoyi, et al.
Published: (2025)

Understanding Common Ground Misalignment in Goal-Oriented Dialog: A Case-Study with Ubuntu Chat Logs
by: Sarkar, Rupak, et al.
Published: (2025)

The Dark Side of ChatGPT: Legal and Ethical Challenges from Stochastic Parrots and Hallucination
by: Li, Zihao
Published: (2023)

Context-aware Biases for Length Extrapolation
by: Veisi, Ali, et al.
Published: (2025)

Evaluating the Sensitivity of LLMs to Prior Context
by: Hankache, Robert, et al.
Published: (2025)

Out of the Cage: How Stochastic Parrots Win in Cyber Security Environments
by: Rigaki, Maria, et al.
Published: (2023)

Parrot: A Training Pipeline Enhances Both Program CoT and Natural Language CoT for Reasoning
by: Jin, Senjie, et al.
Published: (2025)

Neither Replacement nor Panacea: Comparing LLM-Based Conversational and Graphical Decision Support in Industrial Tasks
by: Figliè, Roberto, et al.
Published: (2026)

Position: the Stochastic Parrot in the Coal Mine. Model Collapse is a Threat to Low-Resource Communities
by: Jarvis, Devon, et al.
Published: (2026)

RoPE Distinguishes Neither Positions Nor Tokens in Long Contexts, Provably
by: Du, Yufeng, et al.
Published: (2026)

Neither Fugitive nor Free
by: Wong, Edlie L.
Published: (2024)

AI-native Memory: A Pathway from LLMs Towards AGI
by: Shang, Jingbo, et al.
Published: (2024)

The Stochastic Parrot on LLM's Shoulder: A Summative Assessment of Physical Concept Understanding
by: Yu, Mo, et al.
Published: (2025)

Towards New Benchmark for AI Alignment & Sentiment Analysis in Socially Important Issues: A Comparative Study of Human and LLMs in the Context of AGI
by: Bojic, Ljubisa, et al.
Published: (2025)

Evaluating the Ability of LLMs to Solve Semantics-Aware Process Mining Tasks
by: Rebmann, Adrian, et al.
Published: (2024)