Cover Image

Why are LLMs' abilities emergent?

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Havlík, Vladimír
Format:	Preprint
Published:	2025
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

Large Linguistic Models: Investigating LLMs' metalinguistic abilities
by: Beguš, Gašper, et al.
Published: (2023)

Factors affecting the in-context learning abilities of LLMs for dialogue state tracking
by: Hegde, Pradyoth, et al.
Published: (2025)

Surgical Feature-Space Decomposition of LLMs: Why, When and How?
by: Chavan, Arnav, et al.
Published: (2024)

Look Within, Why LLMs Hallucinate: A Causal Perspective
by: Li, He, et al.
Published: (2024)

Why LLMs Fail at Causal Discovery and How Interventional Agents Escape
by: Roy, Amartya, et al.
Published: (2026)

Why Does New Knowledge Create Messy Ripple Effects in LLMs?
by: Qin, Jiaxin, et al.
Published: (2024)

Why are all LLMs Obsessed with Japanese Culture? On the Hidden Cultural and Regional Biases of LLMs
by: de Landa, Joseba Fernandez, et al.
Published: (2026)

Can AI mimic the human ability to define neologisms?
by: Georgiou, Georgios P.
Published: (2025)

Why LLMs Hallucinate on Structured Knowledge: A Mechanistic Analysis of Reasoning over Linearized Representations
by: Li, Shanghao, et al.
Published: (2026)

LongTail-Swap: benchmarking language models' abilities on rare words
by: Algayres, Robin, et al.
Published: (2025)

On the token distance modeling ability of higher RoPE attention dimension
by: Hong, Xiangyu, et al.
Published: (2024)

Accommodation and Epistemic Vigilance: A Pragmatic Account of Why LLMs Fail to Challenge Harmful Beliefs
by: Cheng, Myra, et al.
Published: (2026)

Semantic Anchors in In-Context Learning: Why Small LLMs Cannot Flip Their Labels
by: Kumar, Anantha Padmanaban Krishna
Published: (2025)

Adaptation Odyssey in LLMs: Why Does Additional Pretraining Sometimes Fail to Improve?
by: Öncel, Fırat, et al.
Published: (2024)

Why We Need World Models for AGI: Where LLMs Fail and How World Models May Outperform
by: Alaswad, Feisal, et al.
Published: (2026)

SLPL SHROOM at SemEval2024 Task 06: A comprehensive study on models ability to detect hallucination
by: Fallah, Pouya, et al.
Published: (2024)

Why Attend to Everything? Focus is the Key
by: Yao, Hengshuai, et al.
Published: (2026)

Code Summarization Beyond Function Level
by: Makharev, Vladimir, et al.
Published: (2025)

Why Slop Matters
by: Kommers, Cody, et al.
Published: (2025)

Why Chain of Thought Fails in Clinical Text Understanding
by: Wu, Jiageng, et al.
Published: (2025)

Why Braking? Scenario Extraction and Reasoning Utilizing LLM
by: Wu, Yin, et al.
Published: (2025)

Left-right asymmetry in predicting brain activity from LLMs' representations emerges with their formal linguistic competence
by: Bonnasse-Gahot, Laurent, et al.
Published: (2026)

Semantic Gravity Wells: Why Negative Constraints Backfire
by: Rana, Shailesh
Published: (2026)

Why is constrained neural language generation particularly challenging?
by: Garbacea, Cristina, et al.
Published: (2022)

Why Do LLMs Struggle in Strategic Play? Broken Links Between Observations, Beliefs, and Actions
by: Sobotka, Jan, et al.
Published: (2026)

Why Retrieval-Augmented Generation Fails: A Graph Perspective
by: Guo, Kai, et al.
Published: (2026)

The Stepwise Informativeness Assumption: Why are Entropy Dynamics and Reasoning Correlated in LLMs?
by: Català, Mar Gonzàlez I, et al.
Published: (2026)

Attention Basin: Why Contextual Position Matters in Large Language Models
by: Yi, Zihao, et al.
Published: (2025)

Why Did Apple Fall: Evaluating Curiosity in Large Language Models
by: Wang, Haoyu, et al.
Published: (2025)

From What to Why: Thought-Space Recommendation with Small Language Models
by: Biswas, Prosenjit, et al.
Published: (2025)

LLM Olympiad: Why Model Evaluation Needs a Sealed Exam
by: Cruz, Jan Christian Blaise, et al.
Published: (2026)

The Why Behind the Action: Unveiling Internal Drivers via Agentic Attribution
by: Qian, Chen, et al.
Published: (2026)

Revealing emergent human-like conceptual representations from language prediction
by: Xu, Ningyu, et al.
Published: (2025)

Tracing the ongoing emergence of human-like reasoning in Large Language Models
by: Morosi, Paolo, et al.
Published: (2026)

Straight to Zero: Why Linearly Decaying the Learning Rate to Zero Works Best for LLMs
by: Bergsma, Shane, et al.
Published: (2025)

Valley: Video Assistant with Large Language model Enhanced abilitY
by: Luo, Ruipu, et al.
Published: (2023)

A Theoretical Analysis of Why Masked Diffusion Models Mitigate the Reversal Curse
by: Jeon, Moongyu, et al.
Published: (2026)

Why Diffusion Language Models Struggle with Truly Parallel (Non-Autoregressive) Decoding?
by: Li, Pengxiang, et al.
Published: (2026)

CrisiText: A dataset of warning messages for LLM training in emergency communication
by: Gonella, Giacomo, et al.
Published: (2025)

Can LLMs Correct Themselves? A Benchmark of Self-Correction in LLMs
by: Tie, Guiyao, et al.
Published: (2025)