Emergent Abilities in Language Models

Latest papers

9 papers1 paper in the last four weeks, with none the four weeks before. 0.0% of all new papers.

On Emergent Capabilities and Model Merging
Sep 21, 2026Luca Zhou, Emanuele RodolàEmergent Abilities in Language Models Emergent Misalignment in Language Models
Sapienza University of Rome · Paradigma
Semantic Lenia: Emergence of Homeostatic Solitons within the Semantic Space of Large Language Models
Aug 12, 2026Yoshihiko KayamaEmergent Abilities in Language Models Language Model Steering
BAIKA Women’s University 2–19–5, Ibaraki, Osaka, Japan
CurveShift: Is Agent Progress Scalar? Separating Level from Shape
Jul 31, 2026Hanwen Xing, Pengyun Wang, BingXu Meng +8Emergent Abilities in Language Models LLM Evaluation
University of Southern California · University of Chicago · University of California, Berkeley +6
Ring-Zero: Scaling Zero RL to a Trillion Parameters for Emergent Reasoning
Jul 14, 2026Xinyu Tang, Qianggang Cao, Yurou Liu +13Emergent Abilities in Language Models RL for Language Models
1Gaoling School of Artificial Intelligence, Renmin University of China · 2Ant Group · 3Tsinghua University +1
Understanding Large Language Models
Jul 1, 2026Yannik Keller, Thomas EisenmannEmergent Abilities in Language Models LLM Interpretability
Emergent Capabilities Arise Randomly from Learning Sparse Attention Patterns
Jun 23, 2026Vatsal Baherwani, Zixi Chen, Shikai Qiu +2Emergent Abilities in Language Models Language Model Scaling Laws
New York University
Finite Certificates for In-Context Determinacy and a Threshold Theory of Emergence in Language Models
May 30, 2026Faruk Alpay, Hamdi AlakkadEmergent Abilities in Language Models LLM Evaluation
Department of Computer Engineering Bahcesehir University, Istanbul, Turkey · Department of Artificial Intelligence Engineering Bahcesehir University, Istanbul, Turkey
What do Language Models Learn and When? The Implicit Curriculum Hypothesis
Apr 9, 2026Emmy Liu, Kaiser Sun, Millicent Li +4Emergent Abilities in Language Models Language Model Pretraining
Language Technologies Institute, Carnegie Mellon University · Department of Computer Science, Data Science and AI Institute, Johns Hopkins University · Khoury College of Computer Science, Northeastern University +1
Stochastic CHAOS: Why Deterministic Inference Kills, and Distributional Variability Is the Heartbeat of Artifical Cognition
Jan 12, 2026Tanmay Joshi, Shourya Aggarwal, Anusa Saha +7Emergent Abilities in Language Models LLM Reliability
Pragya Lab, BITS Pilani Goa, India · Raapid Lab, USA · Apple, USA +1

Sep 21, 2026J/K move · Enter open · S save

On Emergent Capabilities and Model Merging

Luca Zhou, Emanuele Rodolà

Sapienza University of Rome · Paradigma

Emergent Abilities in Language Models Emergent Misalignment in Language Models Language Modeling Language Model Merging Model Merging

Open paper AskPDF arXiv

Fine-tuned checkpoints and adapters now fill public repositories, and the most common operation applied to these artifacts is model merging: arithmetic on their weights that assembles capabilities cheaply. We ask what this operation does to emergent capabilities: behaviors an artifact carries that were never an explicit training target. Studying two independent testbeds (activation oracles and emergent-misaligned models) across three model families, we find that the answer is threefold. First, merging preserves an emergent capability that both parents carry: merging two misaligned checkpoints retains most of their broad misalignment across the whole mixing range. Second, merging cannot create an emergent capability that is superadditive in its parents: no weighted merge of two single-task oracles reaches the jointly-trained oracle's auditing ability. Third, when only one parent carries the capability, merging dilutes it faster than the trained capability that accompanies it: the gap is significant in most settings. In short, emergent behaviors of an artifact do not compose the way its trained capability does.