Learnable Assessment Skills for LLM-based Automated Scoring: Rubric Construction via Iterative Optimization

• URL: http://arxiv.org/abs/2605.29274v1
• Date: Thu, 28 May 2026 02:50:07 GMT
• Title: Learnable Assessment Skills for LLM-based Automated Scoring: Rubric Construction via Iterative Optimization
• Abstract summary: We propose an iterative framework that decomposes a skill into a fixed scaffold and learnable item-agnostic rules.<n>Cross-item transfer experiments reveal that learned skills capture both generalizable and item-specific patterns.
• Score: 31.444113318748588
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: LLM-based automated scoring approaches near-human performance, but scaling to new tasks remains bottlenecked by the per-item human configuration of upstream stages such as rubric construction. Human experts bypass this bottleneck through evaluation heuristics developed over extensive practice. We ask whether LLMs can learn similar heuristics directly from scoring experience, and formalize this as the concept of assessment skills: item-independent natural-language procedural knowledge that guides LLMs through specific stages of the scoring workflow. Focusing on rubric construction as a first instantiation, we propose an iterative framework that decomposes a skill into a fixed scaffold and learnable item-agnostic rules, refining the rules through LLM-driven diagnosis of scoring errors and validation-gated selection. The framework requires no expert-written rubric. On all ten ASAP-SAS items, optimized skills substantially improve LLM-based scoring and frequently surpass the dataset-provided expert rubric. Cross-item transfer experiments further reveal that learned skills capture both generalizable and item-specific patterns.

Related papers

• Beyond Basic Specifications? A Systematic Study of Logical Constructs in LLM-based Specification Generation [29.231420590756954]
  Large language models (LLMs) for the automatic generation of program specifications has emerged as a promising avenue for enhancing verification efficiency.<n>We propose incorporating logical constructs into existing LLM-based specification generation framework.<n>We conduct an empirical study aimed at exploring the impact of various types of syntactic constructs on specification generation framework.
  arXiv  Detail & Related papers  (2026-01-31T13:19:40Z)
• Iterative Self-Incentivization Empowers Large Language Models as Agentic Searchers [74.17516978246152]
  Large language models (LLMs) have been widely integrated into information retrieval to advance traditional techniques.<n>We propose EXSEARCH, an agentic search framework, where the LLM learns to retrieve useful information as the reasoning unfolds.<n>Experiments on four knowledge-intensive benchmarks show that EXSEARCH substantially outperforms baselines.
  arXiv  Detail & Related papers  (2025-05-26T15:27:55Z)
• IDA-Bench: Evaluating LLMs on Interactive Guided Data Analysis [60.32962597618861]
  IDA-Bench is a novel benchmark evaluating large language models in multi-round interactive scenarios.<n>Agent performance is judged by comparing its final numerical output to the human-derived baseline.<n>Even state-of-the-art coding agents (like Claude-3.7-thinking) succeed on 50% of the tasks, highlighting limitations not evident in single-turn tests.
  arXiv  Detail & Related papers  (2025-05-23T09:37:52Z)
• SCAN: Structured Capability Assessment and Navigation for LLMs [54.54085382131134]
  textbfSCAN (Structured Capability Assessment and Navigation) is a practical framework that enables detailed characterization of Large Language Models.<n>SCAN incorporates four key components:.<n>TaxBuilder, which extracts capability-indicating tags from queries to construct a hierarchical taxonomy;.<n>RealMix, a query synthesis and filtering mechanism that ensures sufficient evaluation data for each capability tag;.<n>A PC$2$-based (Pre-Comparison-derived Criteria) LLM-as-a-Judge approach achieves significantly higher accuracy compared to classic LLM-as-a-Judge method
  arXiv  Detail & Related papers  (2025-05-10T16:52:40Z)
• From Course to Skill: Evaluating LLM Performance in Curricular Analytics [2.5104969073405976]
  Large language models (LLMs) are promising for handling large-scale, unstructured curriculum data.<n>We systematically evaluate four text alignment strategies based on LLMs or traditional NLP methods for skill extraction.<n>Our findings highlight the promise of LLMs in analyzing brief and abstract curriculum documents, but also reveal that their performance can vary significantly depending on model selection and prompting strategies.
  arXiv  Detail & Related papers  (2025-05-05T02:46:23Z)
• MoRE-LLM: Mixture of Rule Experts Guided by a Large Language Model [54.14155564592936]
  We propose a Mixture of Rule Experts guided by a Large Language Model (MoRE-LLM)<n>MoRE-LLM steers the discovery of local rule-based surrogates during training and their utilization for the classification task.<n>LLM is responsible for enhancing the domain knowledge alignment of the rules by correcting and contextualizing them.
  arXiv  Detail & Related papers  (2025-03-26T11:09:21Z)
• Latent Factor Models Meets Instructions: Goal-conditioned Latent Factor Discovery without Task Supervision [50.45597801390757]
  Instruct-LF is a goal-oriented latent factor discovery system.<n>It integrates instruction-following ability with statistical models to handle noisy datasets.
  arXiv  Detail & Related papers  (2025-02-21T02:03:08Z)
• Efficient Dynamic Ensembling for Multiple LLM Experts [44.41847678666002]
  Ensemble reasoning for the strengths of different LLM experts is critical to achieving consistent and satisfactory performance on diverse inputs.<n>We propose an efficient Dynamic Ensemble Reasoning paradigm, called DER, to integrate the strengths of multiple LLM experts conditioned on dynamic inputs.<n> Experiments demonstrate that our method uses fewer computational resources to achieve better performance compared to state-of-the-art baselines.
  arXiv  Detail & Related papers  (2024-12-10T12:05:56Z)
• Reasoning Factual Knowledge in Structured Data with Large Language Models [26.00548862629018]
  Large language models (LLMs) have made remarkable progress in various natural language processing tasks. Structured data possesses unique characteristics that differ from the unstructured texts used for pretraining. We propose a benchmark named StructFact to evaluate the structural reasoning capabilities of LLMs in inferring factual knowledge.
  arXiv  Detail & Related papers  (2024-08-22T08:05:09Z)
• Knowledge Plugins: Enhancing Large Language Models for Domain-Specific Recommendations [50.81844184210381]
  We propose a general paradigm that augments large language models with DOmain-specific KnowledgE to enhance their performance on practical applications, namely DOKE. This paradigm relies on a domain knowledge extractor, working in three steps: 1) preparing effective knowledge for the task; 2) selecting the knowledge for each specific sample; and 3) expressing the knowledge in an LLM-understandable way.
  arXiv  Detail & Related papers  (2023-11-16T07:09:38Z)
• FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets [69.91340332545094]
  We introduce FLASK, a fine-grained evaluation protocol for both human-based and model-based evaluation. We experimentally observe that the fine-graininess of evaluation is crucial for attaining a holistic view of model performance.
  arXiv  Detail & Related papers  (2023-07-20T14:56:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.