# Judge Like Human Examiners: A Weighted Importance Multi-Point Evaluation Framework for Generative Tasks with Long-form Answers

arXiv: https://arxiv.org/abs/2604.11246 · HTML: https://mlsanity.com/paper/2604.11246/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 31 of its 84 references that are in the map.
- First posted on arXiv 13 Apr 2026.

## Builds on (most cited first, 30 of 31)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools](https://mlsanity.com/paper/2406.12793/) (2024)
- [BARTScore: Evaluating Generated Text as Text Generation](https://mlsanity.com/paper/2106.11520/) (2021)
- [Prometheus: Inducing Fine-grained Evaluation Capability in Language Models](https://mlsanity.com/paper/2310.08491/) (2023)
- [Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models](https://mlsanity.com/paper/2405.01535/) (2024)
- [MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distance](https://mlsanity.com/paper/1909.02622/) (2019)
- [Judging the Judges: A Systematic Study of Position Bias in LLM-as-a-Judge](https://mlsanity.com/paper/2406.07791/) (2024)
- [Towards a Unified Multi-Dimensional Evaluator for Text Generation](https://mlsanity.com/paper/2210.07197/) (2022)
- [L-Eval: Instituting Standardized Evaluation for Long Context Language Models](https://mlsanity.com/paper/2307.11088/) (2023)
- [FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets](https://mlsanity.com/paper/2307.10928/) (2023)
- [A Survey of Evaluation Metrics Used for NLG Systems](https://mlsanity.com/paper/2008.12009/) (2020)
- [TICKing All the Boxes: Generated Checklists Improve LLM Evaluation and Generation](https://mlsanity.com/paper/2410.03608/) (2024)
- [Atomic Fact Decomposition Helps Attributed Question Answering](https://mlsanity.com/paper/2410.16708/) (2024)
- [AutoSCORE: Enhancing Automated Scoring with Multi-Agent Large Language Models via Structured Component Recognition](https://mlsanity.com/paper/2509.21910/) (2025)
- [Self-Taught Agentic Long Context Understanding](https://mlsanity.com/paper/2502.15920/) (2025)
- [Learning When to Retrieve, What to Rewrite, and How to Respond in Conversational QA](https://mlsanity.com/paper/2409.15515/) (2024)
- [Are Checklists Really Useful for Automatic Evaluation of Generative Tasks?](https://mlsanity.com/paper/2508.15218/) (2025)
- [Evaluation of Question Generation Needs More References](https://mlsanity.com/paper/2305.16626/) (2023)
- [Revisiting In-Context Learning with Long Context Language Models](https://mlsanity.com/paper/2412.16926/) (2024)
- [The Essence of Contextual Understanding in Theory of Mind: A Study on Question Answering with Story Characters](https://mlsanity.com/paper/2501.01705/) (2025)
- [MiniLongBench: The Low-cost Long Context Understanding Benchmark for Large Language Models](https://mlsanity.com/paper/2505.19959/) (2025)
- [PRELUDE: A Benchmark Designed to Require Global Comprehension and Reasoning over Long Contexts](https://mlsanity.com/paper/2508.09848/) (2025)
- [Human vs Automatic Metrics: on the Importance of Correlation Design](https://mlsanity.com/paper/1805.11474/) (2018)
- [Self-Reasoning Language Models: Unfold Hidden Reasoning Chains with Few Reasoning Catalyst](https://mlsanity.com/paper/2505.14116/) (2025)
- [L-CiteEval: Do Long-Context Models Truly Leverage Context for Responding?](https://mlsanity.com/paper/2410.02115/) (2024)
- [Long-Form Information Alignment Evaluation Beyond Atomic Facts](https://mlsanity.com/paper/2505.15792/) (2025)

## Abstract (arXiv)

Evaluating the quality of model responses remains challenging in generative tasks with long-form answers, as the expected answers usually contain multiple semantically distinct yet complementary factors that should be factorized for fine-grained assessment. Recent evaluation methods resort to relying on either task-level rubrics or question-aware checklists. However, they still 1) struggle to assess whether a response is genuinely grounded in provided contexts; 2) fail to capture the heterogeneous importance of different aspects of reference answers. Inspired by human examiners, we propose a Weighted Importance Multi-Point Evaluation (WIMPE) framework, which factorizes each reference answer into weighted context-bound scoring points. Two complementary metrics, namely Weighted Point-wise Alignment (WPA) and Point-wise Conflict Penalty (PCP), are designed to measure the alignment and contradiction between model responses and reference answers. Extensive experiments on 10 generative tasks demonstrate that WIMPE achieves higher correlations with human annotations.