Entity · technique

LANG

techniqueactivelang-0afa4afc·1 events·first seen May 22, 2026

Aliases: LANG

Co-occurring entities

large language models multilingual mathematical benchmarks progressive decay schedule language-adaptive switch Reinforcement Learning

More like this (12)

SGLang LayoutReader vision-language grounding LangMAP TileLang LLVM RING Loong LOOP Langfuse Mandarin Chinese LangChain

Recent events (1)

6arXiv · cs.CL·May 22, 2026·source ↗

LANG: Reinforcement Learning Framework for Multilingual Reasoning with Language-Adaptive Hint Guidance

LANG is a new RL-based framework for improving multilingual reasoning in LLMs that addresses the trade-off between input-language consistency and reasoning quality. It uses language-conditioned hints with a progressive decay schedule and a language-adaptive switch to tailor learning to per-language difficulty. Empirical results on multilingual mathematical benchmarks show improved reasoning without language drift toward English, and the approach generalizes beyond mathematics.

Evaluation and Benchmarking Alignment and RLHF large language models LANG multilingual mathematical benchmarks +3 more