APTER: Adaptive Post-Training with Expert-Grounded Rubrics
As large language models enter professional domains, they must satisfy domain constraints, include critical evidence, and provide complete reasoning rather than merely produce fluent responses. Existing post-training methods often rely on holistic preferences or outcome-level verification, while recent rubric-based methods usually generate rubrics independently for each query. In specialized domains, such unconstrained rubrics may omit critical requirements and vary across samples, hindering the diagnosis and targeted repair of persistent capability deficiencies. We propose APTER (Adaptive Post-Training with Expert-Grounded Rubrics), a framework that integrates structured domain knowledge into fine-grained evaluation, optimization, and diagnosis for specialized complex reasoning. First, expert-grounded rubric construction starts from an expert criteria framework built by domain experts, where each criterion represents a stable professional capability. For each query, APTER selects relevant criteria and instantiates them into query-level rubrics linked to their source criteria, turning reusable expert criteria into executable query-level supervision without reference answers. Second, adaptive post-training uses rubric verdicts as both optimization and criterion-level diagnostic signals. Aggregating low-scoring verdicts by criterion ID reveals persistent deficiencies and triggers targeted supervised fine-tuning updates during reinforcement learning. Experiments on mathematical reasoning and medical question answering show consistent gains across both domains. Across three model generations, APTER improves the mathematics and medical averages over the corresponding base models by up to 15.86 and 8.04 points, respectively. Code and rubric datasets are available at https://github.com/AntDT-APTER/APTER.
Code (0)
등록된 구현이 없습니다.
Tasks
Mathematical ReasoningReinforcement LearningQuestion AnsweringSimilar Papers 제목 키워드 기반
Quant Experts: Token-aware Adaptive Error Reconstruction with Mixture of Experts for Large Vision-Language Models Quantization
Post-Training Quantization (PTQ) has emerged as an effective technique for alleviating the substantial computational and memory overheads of Vision-Language Models (VLMs) by compressing both weights and activations witho…
Retrieval-Free Knowledge-Grounded Dialogue Response Generation with Adapters
To diversify and enrich generated dialogue responses, knowledge-grounded dialogue has been investigated in recent years. The existing methods tackle the knowledge grounding challenge by retrieving the relevant sentences …
Response GenerationRetrievalFrom Isolation to Integration: Building an Adaptive Expert Forest for Pre-Trained Model-based Class-Incremental Learning
Class-Incremental Learning (CIL) requires models to learn new classes without forgetting old ones. A common method is to freeze a pre-trained model and train a new, lightweight adapter for each task. While this prevents …
class-incremental learningLiME: Lightweight Mixture of Experts for Efficient Multimodal Multi-task Learning
MoE-PEFT methods combine Mixture of Experts with parameter-efficient fine-tuning for multi-task adaptation, but require separate adapters per expert causing trainable parameters to scale linearly with expert count and li…
parameter-efficient fine-tuningMulti-Task LearningAdaptive Minds: Empowering Agents with LoRA-as-Tools
We investigate a framework in which LoRA adapters are treated as callable tools that a base language model can dynamically select and invoke. We hypothesize that, when adapters are trained to provide strong domain-specif…