ufakzeka-karar: An Open Turkish Typed-Decision Model with Order-Invariant Option Scoring
cs.CL, cs.LG
Submitted: 2026-10-05
Updated: 2026-10-05
Code: https://github.com/ufakai/ufakzeka-karar
Sources
- ufakzeka-1: Building and Evaluating a 151M-Parameter Turkish Language Model from Scratch
- HakemBench: A Turkish Benchmark of Typed Decisions
- Large Language Models Sensitivity to The Order of Options in Multiple-Choice Questions
- Set-LLM: A Permutation-Invariant LLM
- A, B, C, or Stable? Accuracy and Order Sensitivity Diverge in LLM Multiple-Choice Evaluation
- Balancing Classification and Calibration Performance in Decision-Making LLMs via Calibration Aware Reinforcement Learning
- Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs
- Decoupled Weight Decay Regularization
- On Calibration of Modern Neural Networks
- A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
- DOCTOR: A Simple Method for Detecting Misclassification Errors
- Selective Classification for Deep Neural Networks
- Rethinking Early Stopping: Refine, Then Calibrate
- Smooth ECE: Principled Reliability Diagrams via Kernel Smoothing
- Overcoming Common Flaws in the Evaluation of Selective Classification Systems
- MoganBert-TR: A Turkish Encoder Foundation Model Trained from Scratch with a CLM-to-MLM Curriculum
- Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics
- Shortcut Learning in Deep Neural Networks
- MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languages
- MFAQ: a Multilingual FAQ Dataset
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering