Search papers, labs, and topics across Lattice.
This paper introduces a lightweight adaptation framework for LLMs in technical service domains, addressing the challenges of implicit decision logic and noisy human demonstrations. The framework incorporates Latent Logic Augmentation via Planning-Aware Trajectory Modeling and Decision Reasoning Augmentation, alongside Robust Noise Reduction using a dual-filtering method to construct a Multiple Ground Truths dataset. A Hybrid Reward mechanism, combining an LLM-based judge with a lightweight relevance-based Reranker, achieves comparable alignment to standard LLM-as-a-judge methods with reduced training time.
Achieve SOTA LLM alignment in complex technical domains with a fraction of the compute by distilling knowledge into smaller models using a hybrid reward mechanism and targeted data augmentation.
Adapting Large Language Models in complex technical service domains is constrained by the absence of explicit cognitive chains in human demonstrations and the inherent ambiguity arising from the diversity of valid responses. These limitations severely hinder agents from internalizing latent decision dynamics and generalizing effectively. Moreover, practical adaptation is often impeded by the prohibitive resource and time costs associated with standard training paradigms. To overcome these challenges and guarantee computational efficiency, we propose a lightweight adaptation framework comprising three key contributions. (1) Latent Logic Augmentation: We introduce Planning-Aware Trajectory Modeling and Decision Reasoning Augmentation to bridge the gap between surface-level supervision and latent decision logic. These approaches strengthen the stability of Supervised Fine-Tuning alignment. (2) Robust Noise Reduction: We construct a Multiple Ground Truths dataset through a dual-filtering method to reduce the noise by validating diverse responses, thereby capturing the semantic diversity. (3) Lightweight Adaptation: We design a Hybrid Reward mechanism that fuses an LLM-based judge with a lightweight relevance-based Reranker to distill high-fidelity reward signals while reducing the computational cost compared to standard LLM-as-a-Judge reinforcement learning. Empirical evaluations on real-world Cloud service tasks, conducted across semantically diverse settings, demonstrate that our framework achieves stability and performance gains through Latent Logic Augmentation and Robust Noise Reduction. Concurrently, our Hybrid Reward mechanism achieves alignment comparable to standard LLM-as-a-judge methods with reduced training time, underscoring the practical value for deploying technical service agents.
