Imagen de Portada

Making Bielik LLM Reason (Better): A Field Report

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Trybus, Adam, Bartnicki, Bartosz, Kinas, Remigiusz
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Bielik v3 Small: Technical Report
por: Ociepa, Krzysztof, et al.
Publicado: (2025)

Bielik 11B v2 Technical Report
por: Ociepa, Krzysztof, et al.
Publicado: (2025)

Bielik 11B v3: Multilingual Large Language Model for European Languages
por: Ociepa, Krzysztof, et al.
Publicado: (2025)

Bielik 7B v0.1: A Polish Language Model -- Development, Insights, and Evaluation
por: Ociepa, Krzysztof, et al.
Publicado: (2024)

Advancing Polish Language Modeling through Tokenizer Optimization in the Bielik v3 7B and 11B Series
por: Ociepa, Krzysztof, et al.
Publicado: (2026)

Bielik-Minitron-7B: Compressing Large Language Models via Structured Pruning and Knowledge Distillation for the Polish Language
por: Kinas, Remigiusz, et al.
Publicado: (2026)

Three-Dimensional Affine Spatial Logics
por: Trybus, Adam
Publicado: (2026)

Learning From Mistakes Makes LLM Better Reasoner
por: An, Shengnan, et al.
Publicado: (2023)

Punctuation patterns in "Finnegans Wake" by James Joyce are largely translation-invariant
por: Bartnicki, Krzysztof, et al.
Publicado: (2025)

Bielik Guard: Efficient Polish Language Safety Classifiers for LLM Content Moderation
por: Wróbel, Krzysztof, et al.
Publicado: (2026)

Hint Tuning: Less Data Makes Better Reasoners
por: Fan, Siqi, et al.
Publicado: (2026)

In Their Own Words: Reasoning Traces Tailored for Small Models Make Them Better Reasoners
por: Kim, Jaehoon, et al.
Publicado: (2025)

Abstraction-of-Thought Makes Language Models Better Reasoners
por: Hong, Ruixin, et al.
Publicado: (2024)

Making Long-Context Language Models Better Multi-Hop Reasoners
por: Li, Yanyang, et al.
Publicado: (2024)

Making Large Language Models Better Reasoners with Orchestrated Streaming Experiences
por: Liu, Xiangyang, et al.
Publicado: (2025)

When Less Language is More: Language-Reasoning Disentanglement Makes LLMs Better Multilingual Reasoners
por: Zhao, Weixiang, et al.
Publicado: (2025)

AnnoLLM: Making Large Language Models to Be Better Crowdsourced Annotators
por: He, Xingwei, et al.
Publicado: (2023)

RankPrompt: Step-by-Step Comparisons Make Language Models Better Reasoners
por: Hu, Chi, et al.
Publicado: (2024)

Learning to Self-Verify Makes Language Models Better Reasoners
por: Chen, Yuxin, et al.
Publicado: (2026)

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

FABSVer: Faster Training and Better Self-Verification for LLM Mathematical Reasoning
por: Pan, Haihui, et al.
Publicado: (2026)

Explicit Reasoning Makes Better Judges: A Systematic Study on Accuracy, Efficiency, and Robustness
por: Jayarao, Pratik, et al.
Publicado: (2025)

Better LLM Reasoning via Dual-Play
por: Zhang, Zhengxin, et al.
Publicado: (2025)

Mentor-KD: Making Small Language Models Better Multi-step Reasoners
por: Lee, Hojae, et al.
Publicado: (2024)

Self-Correction Makes LLMs Better Parsers
por: Zhang, Ziyan, et al.
Publicado: (2025)

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

A Non-Binary Method for Finding Interpolants: Theory and Practice
por: Trybus, Adam, et al.
Publicado: (2026)

Learning From Correctness Without Prompting Makes LLM Efficient Reasoner
por: Yao, Yuxuan, et al.
Publicado: (2024)

People Make Better Edits: Measuring the Efficacy of LLM-Generated Counterfactually Augmented Data for Harmful Language Detection
por: Sen, Indira, et al.
Publicado: (2023)

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

Strategic Planning and Rationalizing on Trees Make LLMs Better Debaters
por: Wang, Danqing, et al.
Publicado: (2025)

Question Translation Training for Better Multilingual Reasoning
por: Zhu, Wenhao, et al.
Publicado: (2024)

Learning to Insert [PAUSE] Tokens for Better Reasoning
por: Kim, Eunki, et al.
Publicado: (2025)

Smaller, Weaker, Yet Better: Training LLM Reasoners via Compute-Optimal Sampling
por: Bansal, Hritik, et al.
Publicado: (2024)

NeoN: A Tool for Automated Detection, Linguistic and LLM-Driven Analysis of Neologisms in Polish
por: Tomaszewska, Aleksandra, et al.
Publicado: (2025)

Making Large Language Models Perform Better in Knowledge Graph Completion
por: Zhang, Yichi, et al.
Publicado: (2023)

Advantageous Parameter Expansion Training Makes Better Large Language Models
por: Gu, Naibin, et al.
Publicado: (2025)

Evaluating LLM-Generated Q&A Test: a Student-Centered Study
por: Wróblewska, Anna, et al.
Publicado: (2025)

Learning to Adapt SFT Data for Better Reasoning Generalization
por: Sun, Lisong, et al.
Publicado: (2026)

Better Zero-Shot Reasoning with Role-Play Prompting
por: Kong, Aobo, et al.
Publicado: (2023)