Almanac
technique

LANG

techniqueactivelang-0afa4afc·1 events·first seen 25d ago

Aliases: LANG

Co-occurring entities

More like this (12)

Recent events (1)

6arXiv · cs.CL·25d ago·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.