Imagen de Portada

Code Mixologist : A Practitioner's Guide to Building Code-Mixed LLMs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Gupta, Himanshu, Jayarao, Pratik, Dwivedi, Chaitanya, Varshney, Neeraj
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

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

Expert Upcycling: Shifting the Compute-Efficient Frontier of Mixture-of-Experts
por: Dwivedi, Chaitanya, et al.
Publicado: (2026)

Code-Mixer Ya Nahi: Novel Approaches to Measuring Multilingual LLMs' Code-Mixing Capabilities
por: Gupta, Ayushman, et al.
Publicado: (2024)

CodeMixBench: Evaluating Code-Mixing Capabilities of LLMs Across 18 Languages
por: Yang, Yilun, et al.
Publicado: (2025)

PythonSaga: Redefining the Benchmark to Evaluate Code Generating LLMs
por: Yadav, Ankit, et al.
Publicado: (2024)

COMI-LINGUA: Expert Annotated Large-Scale Dataset for Multitask NLP in Hindi-English Code-Mixing
por: Sheth, Rajvee, et al.
Publicado: (2025)

TreeDiff: AST-Guided Code Generation with Diffusion LLMs
por: Zeng, Yiming, et al.
Publicado: (2025)

SAND-Math: Using LLMs to Generate Novel, Difficult and Useful Mathematics Questions and Answers
por: Manem, Chaitanya, et al.
Publicado: (2025)

Multi-task Code LLMs: Data Mix or Model Merge?
por: Zhu, Mingzhi, et al.
Publicado: (2026)

CodeMixBench: Evaluating Large Language Models on Code Generation with Code-Mixed Prompts
por: Sheokand, Manik, et al.
Publicado: (2025)

The Art of Defending: A Systematic Evaluation and Analysis of LLM Defense Strategies on Safety and Over-Defensiveness
por: Varshney, Neeraj, et al.
Publicado: (2023)

Investigating and Addressing Hallucinations of LLMs in Tasks Involving Negation
por: Varshney, Neeraj, et al.
Publicado: (2024)

On Code-Induced Reasoning in LLMs
por: Waheed, Abdul, et al.
Publicado: (2025)

Toward Reliable Clinical Coding with Language Models: Verification and Lightweight Adaptation
por: Yuan, Zhangdie, et al.
Publicado: (2025)

CodeSCM: Causal Analysis for Multi-Modal Code Generation
por: Gupta, Mukur, et al.
Publicado: (2025)

Multilingual Controlled Generation And Gold-Standard-Agnostic Evaluation of Code-Mixed Sentences
por: Gupta, Ayushman, et al.
Publicado: (2024)

CodeBoost: Boosting Code LLMs by Squeezing Knowledge from Code Snippets with RL
por: Wang, Sijie, et al.
Publicado: (2025)

CodeCipher: Learning to Obfuscate Source Code Against LLMs
por: Lin, Yalan, et al.
Publicado: (2024)

Code Needs Comments: Enhancing Code LLMs with Comment Augmentation
por: Song, Demin, et al.
Publicado: (2024)

Evaluation of Code LLMs on Geospatial Code Generation
por: Gramacki, Piotr, et al.
Publicado: (2024)

Code Prompting Elicits Conditional Reasoning Abilities in Text+Code LLMs
por: Puerto, Haritz, et al.
Publicado: (2024)

CodeACT: Code Adaptive Compute-efficient Tuning Framework for Code LLMs
por: Lv, Weijie, et al.
Publicado: (2024)

CodeGraph: Enhancing Graph Reasoning of LLMs with Code
por: Cai, Qiaolong, et al.
Publicado: (2024)

Code LLMs: A Taxonomy-based Survey
por: Raihan, Nishat, et al.
Publicado: (2024)

Enhancing Code LLMs with Reinforcement Learning in Code Generation: A Survey
por: Wang, Junqiao, et al.
Publicado: (2024)

COMMENTATOR: A Code-mixed Multilingual Text Annotation Framework
por: Sheth, Rajvee, et al.
Publicado: (2024)

CodeLutra: Boosting LLM Code Generation via Preference-Guided Refinement
por: Tao, Leitian, et al.
Publicado: (2024)

Code-Mixed Probes Show How Pre-Trained Models Generalise On Code-Switched Text
por: De Leon, Frances A. Laureano, et al.
Publicado: (2024)

CodeIP: A Grammar-Guided Multi-Bit Watermark for Large Language Models of Code
por: Guan, Batu, et al.
Publicado: (2024)

MixSarc: A Bangla-English Code-Mixed Corpus for Implicit Meaning Identification
por: Alam, Kazi Samin Yasar, et al.
Publicado: (2026)

PerfCodeBench: Benchmarking LLMs for System-Level High-Performance Code Optimization
por: Jing, Huihao, et al.
Publicado: (2026)

Building A Coding Assistant via the Retrieval-Augmented Language Model
por: Li, Xinze, et al.
Publicado: (2024)

Code-Mixed Telugu-English Hate Speech Detection
por: Kakarla, Santhosh, et al.
Publicado: (2025)

Linguistics Theory Meets LLM: Code-Switched Text Generation via Equivalence Constrained Large Language Models
por: Kuwanto, Garry, et al.
Publicado: (2024)

A Practitioner's Guide to Building ASR Models for Low-Resource Languages: A Case Study on Scottish Gaelic
por: Klejch, Ondřej, et al.
Publicado: (2025)

Evaluating and Aligning CodeLLMs on Human Preference
por: Yang, Jian, et al.
Publicado: (2024)

BnSentMix: A Diverse Bengali-English Code-Mixed Dataset for Sentiment Analysis
por: Alam, Sadia, et al.
Publicado: (2024)

CodeElo: Benchmarking Competition-level Code Generation of LLMs with Human-comparable Elo Ratings
por: Quan, Shanghaoran, et al.
Publicado: (2025)

OpenCodeInstruct: A Large-scale Instruction Tuning Dataset for Code LLMs
por: Ahmad, Wasi Uddin, et al.
Publicado: (2025)

\texttt{ReMind}: Understanding Deductive Code Reasoning in LLMs
por: Gao, Jun, et al.
Publicado: (2025)