TARo: Token-level Adaptive Routing for LLM Test-time Alignment
Large language models (LLMs) exhibit strong reasoning capabilities but typically require expensive post-training to reach high performance. Recent test-time alignment methods offer a lightweight alternative, but have been explored mainly for preference alignment rather than reasoning. To bridge this gap, we propose, Token-level Adaptive Routing (TARo), which steers frozen LLMs toward structured reasoning entirely at inference time. Specifically, we first train reward models on step-wise mathematical traces to capture fine-grained logical consistency signals, then introduce a learnable token-level router that automatically controls the guidance of the reward model to the base model. Extensive experiments show that TARo significantly improves reasoning performance by up to +22.4% over base model and +8.4% over existing token-level test-time alignment methods, while also boosting out-of-distribution clinical reasoning (MedXpertQA) and instruction following (AlpacaEval). Furthermore, TARo also generalizes from small to large backbones without retraining, extending test-time alignment from preference optimization to robust, cross-domain reasoning.
Code (0)
등록된 구현이 없습니다.
Tasks
Instruction FollowingSimilar Papers 제목 키워드 기반
Chiaroscuro Attention: Spending Compute in the Dark
We introduce CHIAR-Former (CHIAroscuro Attention-based tRansFormer), an efficient transformer that routes each token to either DCT spectral mixing (O(d log d), sub-quadratic) or full self-attention (O(n^2 d), quadratic i…
TAROT: Test-driven and Capability-adaptive Curriculum Reinforcement Fine-tuning for Code Generation with Large Language Models
Large Language Models (LLMs) are changing the coding paradigm, known as vibe coding, yet synthesizing algorithmically sophisticated and robust code still remains a critical challenge. Incentivizing the deep reasoning cap…
Code GenerationTARO: Temporal Adversarial Rectification Optimization Using Diffusion Models as Purifiers
Adversarial purification with diffusion models seeks to project adversarial examples back toward the data manifold, but balancing semantic preservation and robustness against adaptive attacks remains challenging. Recent …
Learning to Route LLMs from Implicit Cost-Performance Preferences via Meta-Learning
Large language models (LLMs) present a trade-off between performance and cost, where more powerful models incur greater expense. LLM routing aims to mitigate expenses while maintaining performance by sending queries to t…
TARO: Timestep-Adaptive Representation Alignment with Onset-Aware Conditioning for Synchronized Video-to-Audio Synthesis
This paper introduces Timestep-Adaptive Representation Alignment with Onset-Aware Conditioning (TARO), a novel framework for high-fidelity and temporally coherent video-to-audio synthesis. Built upon flow-based transform…
Audio SynthesisFAD