Cover Image

"I've Seen How This Goes": Characterizing Diversity via Progressive Conditional Surprise

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Khoriaty, Matthew, Williams-King, David, Feng, Shi
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

I've Seen the Future, and It's Surprisingly Cheap!
by: Reynolds, Veronica
Published: (2011)

I've got the "Answer"! Interpretation of LLMs Hidden States in Question Answering
by: Goloviznina, Valeriya, et al.
Published: (2024)

Don't Forget It! Conditional Sparse Autoencoder Clamping Works for Unlearning
by: Khoriaty, Matthew, et al.
Published: (2025)

AutoDiscovery: Open-ended Scientific Discovery via Bayesian Surprise
by: Agarwal, Dhruv, et al.
Published: (2025)

A Little Human Data Goes A Long Way
by: Ashok, Dhananjay, et al.
Published: (2024)

Line Goes Up? Inherent Limitations of Benchmarks for Evaluating Large Language Models
by: Fodor, James
Published: (2025)

Calibrated Surprise: An Information-Theoretic Account of Creative Quality
by: Zou, Bo, et al.
Published: (2026)

A Surprising Failure? Multimodal LLMs and the NLVR Challenge
by: Wu, Anne, et al.
Published: (2024)

SR-TTT: Surprisal-Aware Residual Test-Time Training
by: P, Swamynathan V
Published: (2026)

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

Skywork-Math: Data Scaling Laws for Mathematical Reasoning in Large Language Models -- The Story Goes On
by: Zeng, Liang, et al.
Published: (2024)

Prediction Is All MoE Needs: Expert Load Distribution Goes from Fluctuating to Stabilizing
by: Cong, Peizhuang, et al.
Published: (2024)

I've Got 99 Problems But FLOPS Ain't One
by: Gherghescu, Alexandru M., et al.
Published: (2024)

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

Minimal and Mechanistic Conditions for Behavioral Self-Awareness in LLMs
by: Bozoukov, Matthew, et al.
Published: (2025)

Explicit Diversity Conditions for Effective Question Answer Generation with Large Language Models
by: Yadav, Vikas, et al.
Published: (2024)

Recursive Language Models Meet Uncertainty: The Surprising Effectiveness of Self-Reflective Program Search for Long Context
by: Alizadeh, Keivan, et al.
Published: (2026)

A Method for Characterizing Disease Progression from Acute Kidney Injury to Chronic Kidney Disease
by: Fang, Yilu, et al.
Published: (2025)

Reasoning, Code, or Both? How Large Language Models Handle Variations in Math Questions
by: Kutakh, Matthew
Published: (2026)

Automated Rewards via LLM-Generated Progress Functions
by: Sarukkai, Vishnu, et al.
Published: (2024)

Qwen Goes Brrr: Off-the-Shelf RAG for Ukrainian Multi-Domain Document Understanding
by: Bazdyrev, Anton, et al.
Published: (2026)

A Little Confidence Goes a Long Way
by: Scoville, John, et al.
Published: (2024)

How do Language Models Bind Entities in Context?
by: Feng, Jiahai, et al.
Published: (2023)

Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training
by: Liu, Mingjie, et al.
Published: (2025)

Elias in the Lighthouse, Again? Diagnosing Low Diversity in LLM Stories
by: Hamilton, Sil, et al.
Published: (2026)

PPSEBM: An Energy-Based Model with Progressive Parameter Selection for Continual Learning
by: Li, Xiaodi, et al.
Published: (2025)

Text Diffusion with Reinforced Conditioning
by: Liu, Yuxuan, et al.
Published: (2024)

Lean-ing on Quality: How High-Quality Data Beats Diverse Multilingual Data in AutoFormalization
by: Chan, Willy, et al.
Published: (2025)

Incremental Summarization for Customer Support via Progressive Note-Taking and Agent Feedback
by: Wu, Yisha, et al.
Published: (2025)

Improving Multilingual Instruction Finetuning via Linguistically Natural and Diverse Datasets
by: Indurthi, Sathish Reddy, et al.
Published: (2024)

On The Truthfulness of 'Surprisingly Likely' Responses of Large Language Models
by: Goel, Naman
Published: (2023)

Affinity and Diversity: A Unified Metric for Demonstration Selection via Internal Representations
by: Kato, Mariko, et al.
Published: (2025)

Annotation-Efficient Language Model Alignment via Diverse and Representative Response Texts
by: Jinnai, Yuu, et al.
Published: (2024)

Training Reasoning Models on Saturated Problems via Failure-Prefix Conditioning
by: Kim, Minwu, et al.
Published: (2026)

TableDreamer: Progressive and Weakness-guided Data Synthesis from Scratch for Table Instruction Tuning
by: Zheng, Mingyu, et al.
Published: (2025)

Progressive Knowledge Graph Completion
by: Li, Jiayi, et al.
Published: (2024)

Inner Speech as Behavior Guides: Steerable Imitation of Diverse Behaviors for Human-AI coordination
by: Trivedi, Rakshit, et al.
Published: (2026)

Adapting Language Models via Token Translation
by: Feng, Zhili, et al.
Published: (2024)

ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs
by: Chen, Justin Chih-Yao, et al.
Published: (2023)

Scaling Multimodal Search and Recommendation with Small Language Models via Upside-Down Reinforcement Learning
by: Lin, Yu-Chen, et al.
Published: (2025)