Papers with evaluation models
WeCheck: Strong Factual Consistency Checker via Weakly Supervised Learning (2023.acl-long)
Copied to clipboard
| Challenge: | Existing factual consistency metrics are often uncontrollably generating text that is factually inconsistent with inputs. |
| Approach: | They propose a weakly supervised framework that is directly trained on actual generated samples from language models with weakly annotated labels. |
| Outcome: | The proposed framework improves on the TRUE benchmark by 3.3% over existing methods with 435M parameters. |
Speaker Sensitive Response Evaluation Model (2020.acl-main)
Copied to clipboard
| Challenge: | Existing evaluation models rate appropriate responses if they deviate from the ground truth . a limited range of appropriate responses for a given context is needed to evaluate dialogue . |
| Approach: | They propose an automatic evaluation model that considers similarity of generated responses with conversational context and learns parameters from an unlabeled conversation corpus. |
| Outcome: | The proposed model outperforms existing evaluation metrics in terms of correlation with human annotation scores. |
Minos: A Multimodal Evaluation Model for Bidirectional Generation Between Image and Text (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing evaluation models struggle to achieve consistent performance across image-to-text (I2T) and text-to image (T2I) tasks. |
| Approach: | They construct a multimodal evaluation model using a large multimodal dataset and rigorous quality control strategies to train it. |
| Outcome: | The proposed model achieves state-of-the-art evaluation performance across 16 out-of domain datasets covering both I2T and T2I tasks among all open-source multimodal evaluation models and remain competitive with closed-source models. |
Weak Reward Model Transforms Generative Models into Robust Causal Event Extraction Systems (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing evaluation metrics that reflect the performance of causal event extraction tasks are poorly reflecting the inherent ambiguity of cause and effect boundaries. |
| Approach: | They propose to use a weak-to-strong supervision method to train an evaluation model while still achieving high performance in training an RL model. |
| Outcome: | The proposed method achieves high agreement with human-annotated data while still achieving high performance in training an RL model. |
Themis: A Reference-free NLG Evaluation Language Model with Flexibility and Interpretability (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for evaluation of natural language generation tasks lack reliable data. |
| Approach: | They propose to use annotations from human and GPT-4 to construct a corpus for NLG evaluation. |
| Outcome: | The proposed corpus can perform flexible and interpretable evaluations without references and surpasses existing models. |
IF-CRITIC: Towards a Fine-Grained LLM Critic for Instruction-Following Evaluation (2026.acl-long)
Copied to clipboard
Bosi Wen, Yilin Niu, Cunxiang Wang, Pei Ke, Xiaoying Ling, Ying Zhang, Aohan Zeng, Hongning Wang, Minlie Huang
| Challenge: | Existing evaluation models for instruction-following have many shortcomings, such as substantial costs and unreliable assessments. |
| Approach: | They propose an LLM critic for fine-grained instruction-following evaluation using a checklist generator and a constraint-level preference optimization method. |
| Outcome: | The proposed model beats strong LLM-as-a-Judge baselines in evaluations under lower computational overhead compared to baselines. |