arXiv Machine Learning
Jun 10
CodeAlchemy: Synthetic Code Rewriting at Scale
arXiv:2606. 10087v1 Announce Type: cross Abstract: Pre-training on raw code teaches syntax but provides sparse signal for diverse real-world task formats.
Synthetic Hallucinations, Real Gains: Hard Negatives from Frontier Models for FIM Hallucination Mitigation
arXiv:2606. 03130v1 Announce Type: new Abstract: Small open-source code models that power IDE autocomplete still emit hallucinated Fill-in-the-Middle (FIM) completions: syntactically natural calls to methods, parameters, variables, and imports that do not exist in the surrounding project.
Related stories
arXiv Machine Learning
Jul 22
Spaghetti Architect: A Contamination-Resistant, By-Construction-Labelled, Multi-Language Code Dataset Generator
arXiv:2607. 18642v1 Announce Type: new Abstract: Mined code corpora are abundant but uncontrolled: a snippet's semantics, surface "messiness," and difficulty are whatever the wild contained; there is no known-optimal reference to grade against; and any public sample may already sit in a model's training set.
arXiv Machine Learning
Aug 11
MetaLint: Easy-to-Hard Generalization for Code Linting
arXiv:2507. 11687v5 Announce Type: replace-cross Abstract: Large language models excel at code generation but struggle with code linting, particularly in generalizing to unseen or evolving best practices beyond those observed during training.
arXiv AI
Sep 18
QVAC Genesis III: A Large-Scale, High-Quality Open Synthetic STEM Corpus for Efficient Language Model Pre-Training
QVAC Genesis III is a 191.43 B‑token synthetic STEM corpus covering 19 domains and multiple difficulty levels, created through a dual generation strategy that uses a weak edge‑scale student model to generate corrective explanations and contrastive reasoning. The authors evaluate the corpus with an LLM‑as‑a‑parser protocol and demonstrate that 1.7 B‑parameter models trained on QVAC Genesis III outperform those trained on Cosmopedia‑v2 and the Cosmo‑1B model on ARC, GPQA Diamond, and MMLU STEM benchmarks, achieving up to +28.57% improvement on ARC‑E and a 99.45% valid answer rate.
arXiv AI
6d ago
ORCA: Evaluating LLMs on Data Science Code Translation
ORCA is a new benchmark for evaluating large language models on Data Science Code Translation (DSCT), comprising two settings: ORCA-MAIN with 1,600 grounding-level tasks across data querying, manipulation, and deep learning, and ORCA-PROJECT with 200 full-project translation tasks across seven data‑science task types. Each task includes reference translations and test cases to verify functional equivalence, and a multi‑stage quality verification process ensures task correctness. Experiments show that even state‑of‑the‑art LLMs perform poorly on DSCT, with Claude‑Opus‑4.6 achieving only 56.92% success on ORCA‑MAIN and 33.67% on ORCA‑PROJECT, while an intent‑augmented approach improves success rates by 4.80% and 5.33% respectively.
arXiv Machine Learning
Sep 11
Domain-Specific Hallucination Detection in Large Language Models
The paper introduces a multi‑signal pipeline for detecting hallucinations in large language models, combining fine‑tuned DeBERTa‑v3 classification, Monte Carlo Dropout uncertainty, and temperature‑scaled calibration. On the HaluEval benchmark it achieves high performance (F1 = 0.915, AUROC = 0.977) across QA, summarization, and dialogue, and shows that 25 % of training data yields 77 % of full‑data performance. The authors also demonstrate that applying Direct Preference Optimization to a Qwen2.5‑0.5B generator cuts hallucination rates from 85.5 % to 37.7 %, and that domain‑specific fine‑tuning (PubMedBERT on SciFact) outperforms general‑domain models for biomedical text.
arXiv Computation and Language
Sep 15
Lexical Prompt Compression for Large Language Models: A Training-Free, Deterministic Pipeline with Empirical Pareto Analysis Across Eleven Task Categories
arXiv:2609.13154v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) have made prompts increasingly large and complex. Techniques such as chain-of-thought reasoning (Wei et...
arXiv AI
Jul 22
SciCodePile: A 128GB Corpus and Executable Benchmark for Challenging Scientific Code Generation
arXiv:2607. 19104v1 Announce Type: cross Abstract: Large language models (LLMs) excel at general-purpose code generation, yet how well they handle scientific code remains an open question.
arXiv Computation and Language
3d ago
Listening to the Wise Few: Query-Key Alignment Unlocks Latent Correct Answers in Large Language Models
arXiv:2410.02343v2 Announce Type: replace Abstract: Large language models (LLMs) routinely fail to output the correct option in multiple-choice question answering (MCQA) while encoding the answer int...
arXiv AI
Aug 10
Beyond Text Matching: Towards Reference-Free Evaluation for Human-Oriented Binary Reverse Engineering
arXiv:2608. 07038v1 Announce Type: cross Abstract: Human-Oriented Binary Reverse Engineering (HOBRE) aims to transform decompiled pseudocode into a more human-friendly representation, thereby reducing the cognitive burden of reverse analysis and improving efficiency.
Hugging Face Trending Papers
Sep 10
Domain-Specific Hallucination Detection in Large Language Models
The paper introduces a multi‑signal pipeline for detecting hallucinations in large language model outputs, combining fine‑tuned DeBERTa‑v3 classification, Monte Carlo Dropout uncertainty, and temperature‑scaled calibration. On the HaluEval benchmark it achieves strong performance (F1 = 0.915, AUROC = 0.977) and further improves accuracy to 93.2% with MC Dropout. The authors also demonstrate that applying Direct Preference Optimization to a Qwen2.5‑0.5B generator reduces hallucination rates from 85.5% to 37.7%, and show that domain‑specific fine‑tuning (PubMedBERT on SciFact) yields better results than general‑domain training.
arXiv Machine Learning
4d ago
It's All Training: A Fully Synthetic Single-Stage Recipe for LLMs
arXiv:2609.37891v1 Announce Type: cross Abstract: Current pre-training datasets are derived from web crawls, with all their issues, and were not designed to support mid- and post-training pipelines--...