Image de couverture de livre

Making Bielik LLM Reason (Better): A Field Report

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Trybus, Adam, Bartnicki, Bartosz, Kinas, Remigiusz
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Bielik v3 Small: Technical Report
par: Ociepa, Krzysztof, et autres
Publié: (2025)

Bielik 11B v2 Technical Report
par: Ociepa, Krzysztof, et autres
Publié: (2025)

Bielik 11B v3: Multilingual Large Language Model for European Languages
par: Ociepa, Krzysztof, et autres
Publié: (2025)

Bielik 7B v0.1: A Polish Language Model -- Development, Insights, and Evaluation
par: Ociepa, Krzysztof, et autres
Publié: (2024)

Advancing Polish Language Modeling through Tokenizer Optimization in the Bielik v3 7B and 11B Series
par: Ociepa, Krzysztof, et autres
Publié: (2026)

Bielik-Minitron-7B: Compressing Large Language Models via Structured Pruning and Knowledge Distillation for the Polish Language
par: Kinas, Remigiusz, et autres
Publié: (2026)

Three-Dimensional Affine Spatial Logics
par: Trybus, Adam
Publié: (2026)

Learning From Mistakes Makes LLM Better Reasoner
par: An, Shengnan, et autres
Publié: (2023)

Punctuation patterns in "Finnegans Wake" by James Joyce are largely translation-invariant
par: Bartnicki, Krzysztof, et autres
Publié: (2025)

Bielik Guard: Efficient Polish Language Safety Classifiers for LLM Content Moderation
par: Wróbel, Krzysztof, et autres
Publié: (2026)

Hint Tuning: Less Data Makes Better Reasoners
par: Fan, Siqi, et autres
Publié: (2026)

In Their Own Words: Reasoning Traces Tailored for Small Models Make Them Better Reasoners
par: Kim, Jaehoon, et autres
Publié: (2025)

Abstraction-of-Thought Makes Language Models Better Reasoners
par: Hong, Ruixin, et autres
Publié: (2024)

Making Long-Context Language Models Better Multi-Hop Reasoners
par: Li, Yanyang, et autres
Publié: (2024)

Making Large Language Models Better Reasoners with Orchestrated Streaming Experiences
par: Liu, Xiangyang, et autres
Publié: (2025)

When Less Language is More: Language-Reasoning Disentanglement Makes LLMs Better Multilingual Reasoners
par: Zhao, Weixiang, et autres
Publié: (2025)

AnnoLLM: Making Large Language Models to Be Better Crowdsourced Annotators
par: He, Xingwei, et autres
Publié: (2023)

RankPrompt: Step-by-Step Comparisons Make Language Models Better Reasoners
par: Hu, Chi, et autres
Publié: (2024)

Learning to Self-Verify Makes Language Models Better Reasoners
par: Chen, Yuxin, et autres
Publié: (2026)

Pensez: Less Data, Better Reasoning -- Rethinking French LLM
par: Ha, Huy Hoang
Publié: (2025)

FABSVer: Faster Training and Better Self-Verification for LLM Mathematical Reasoning
par: Pan, Haihui, et autres
Publié: (2026)

Explicit Reasoning Makes Better Judges: A Systematic Study on Accuracy, Efficiency, and Robustness
par: Jayarao, Pratik, et autres
Publié: (2025)

Better LLM Reasoning via Dual-Play
par: Zhang, Zhengxin, et autres
Publié: (2025)

Mentor-KD: Making Small Language Models Better Multi-step Reasoners
par: Lee, Hojae, et autres
Publié: (2024)

Self-Correction Makes LLMs Better Parsers
par: Zhang, Ziyan, et autres
Publié: (2025)

Cross-Family Speculative Decoding for Polish Language Models on Apple~Silicon: An Empirical Evaluation of Bielik~11B with UAG-Extended MLX-LM
par: Fonal, Krzysztof
Publié: (2026)

A Non-Binary Method for Finding Interpolants: Theory and Practice
par: Trybus, Adam, et autres
Publié: (2026)

Learning From Correctness Without Prompting Makes LLM Efficient Reasoner
par: Yao, Yuxuan, et autres
Publié: (2024)

People Make Better Edits: Measuring the Efficacy of LLM-Generated Counterfactually Augmented Data for Harmful Language Detection
par: Sen, Indira, et autres
Publié: (2023)

Bielik-Q2-Sharp: A Comparative Study of Extreme 2-bit Quantization Methods for a Polish 11B Language Model
par: Prejzner, Jakub
Publié: (2026)

Strategic Planning and Rationalizing on Trees Make LLMs Better Debaters
par: Wang, Danqing, et autres
Publié: (2025)

Question Translation Training for Better Multilingual Reasoning
par: Zhu, Wenhao, et autres
Publié: (2024)

Learning to Insert [PAUSE] Tokens for Better Reasoning
par: Kim, Eunki, et autres
Publié: (2025)

Smaller, Weaker, Yet Better: Training LLM Reasoners via Compute-Optimal Sampling
par: Bansal, Hritik, et autres
Publié: (2024)

NeoN: A Tool for Automated Detection, Linguistic and LLM-Driven Analysis of Neologisms in Polish
par: Tomaszewska, Aleksandra, et autres
Publié: (2025)

Making Large Language Models Perform Better in Knowledge Graph Completion
par: Zhang, Yichi, et autres
Publié: (2023)

Advantageous Parameter Expansion Training Makes Better Large Language Models
par: Gu, Naibin, et autres
Publié: (2025)

Evaluating LLM-Generated Q&A Test: a Student-Centered Study
par: Wróblewska, Anna, et autres
Publié: (2025)

Learning to Adapt SFT Data for Better Reasoning Generalization
par: Sun, Lisong, et autres
Publié: (2026)

Better Zero-Shot Reasoning with Role-Play Prompting
par: Kong, Aobo, et autres
Publié: (2023)