Evaluating large language models trained on code

Very Large Language Models and How to Evaluate Them

Evaluating Language Model Bias with 🤗 Evaluate

Uncheatable Eval: Dynamic Compression-Based Evaluation of Language Models

Modern large language models are pretrained on massive datasets, making it difficult to prevent benchmark data from entering their training sets and undermining the reliability of evaluation results....

Efficient training of language models to fill in the middle

Learn2Zinc: Fine-tuning Small Language Models for Text-to-Model Translation in MiniZinc

arXiv:2607. 20456v1 Announce Type: cross Abstract: Large language models excel at code generation for mainstream programming languages but struggle with rare, domain-specific languages such as MiniZinc, a constraint modeling language for combinatorial problems.

Uncheatable Eval: Dynamic Compression-Based Evaluation of Language Models

arXiv:2609.27510v1 Announce Type: cross Abstract: Modern large language models are pretrained on massive datasets, making it difficult to prevent benchmark data from entering their training sets and...

Uncovering Competency Gaps in Large Language Models and Their Benchmarks

arXiv:2512. 20638v2 Announce Type: replace-cross Abstract: The evaluation of large language models relies heavily on standardized benchmarks.

FindStatBench: Evaluating Large Language Models on Combinatorial Code Synthesis

arXiv:2607. 18260v1 Announce Type: new Abstract: We introduce FindStatBench, an execution benchmark for evaluating large language models on combinatorial code synthesis.

Matryoshka Language Model Suites

arXiv:2608. 09703v1 Announce Type: new Abstract: Training a language model suite classically requires training each model separately and serving them independently.

Red-Teaming Large Language Models

SWE-MERA: A Dynamic Benchmark for Agenticly Evaluating Large Language Models on Software Engineering Tasks

arXiv:2507. 11059v3 Announce Type: replace-cross Abstract: The rapid advancement of Large Language Models (LLMs) in software engineering has revealed critical limitations in existing benchmarks, particularly the widely used SWE-bench dataset.

LuxIT: A Luxembourgish Instruction Tuning Dataset from Monolingual Seed Data

LuxIT is a monolingual instruction‑tuning dataset for Luxembourgish, created by synthesizing instruction‑answer pairs from native texts using the DeepSeek‑R1‑0528 model and a quality‑assurance LLM‑as‑judge process. The resulting 227,507 high‑quality pairs were used to fine‑tune 14 LLMs (≤15 B parameters), yielding an average accuracy increase of +5.37 percentage points on standardized Luxembourgish proficiency exams and improvements in macro‑averaged F1 on nine of the fourteen downstream NLP tasks. These findings demonstrate that synthetic monolingual data can effectively enhance LLM performance in low‑resource languages and reveal the complex relationship between exam performance and practical NLP gains.