HALT-RAG: A Task-Adaptable Framework for Hallucination Detection with Calibrated NLI Ensembles and Abstention
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911144398028800 |
|---|---|
| author | Goswami, Saumya Kurra, Siddharth |
| author_facet | Goswami, Saumya Kurra, Siddharth |
| contents | Detecting content that contradicts or is unsupported by a given source text is a critical challenge for the safe deployment of generative language models. We introduce HALT-RAG, a post-hoc verification system designed to identify hallucinations in the outputs of Retrieval-Augmented Generation (RAG) pipelines. Our flexible and task-adaptable framework uses a universal feature set derived from an ensemble of two frozen, off-the-shelf Natural Language Inference (NLI) models and lightweight lexical signals. These features are used to train a simple, calibrated, and task-adapted meta-classifier. Using a rigorous 5-fold out-of-fold (OOF) training protocol to prevent data leakage and produce unbiased estimates, we evaluate our system on the HaluEval benchmark. By pairing our universal feature set with a lightweight, task-adapted classifier and a precision-constrained decision policy, HALT-RAG achieves strong OOF F1-scores of 0.7756, 0.9786, and 0.7391 on the summarization, QA, and dialogue tasks, respectively. The system's well-calibrated probabilities enable a practical abstention mechanism, providing a reliable tool for balancing model performance with safety requirements. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_07475 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | HALT-RAG: A Task-Adaptable Framework for Hallucination Detection with Calibrated NLI Ensembles and Abstention Goswami, Saumya Kurra, Siddharth Computation and Language Artificial Intelligence Detecting content that contradicts or is unsupported by a given source text is a critical challenge for the safe deployment of generative language models. We introduce HALT-RAG, a post-hoc verification system designed to identify hallucinations in the outputs of Retrieval-Augmented Generation (RAG) pipelines. Our flexible and task-adaptable framework uses a universal feature set derived from an ensemble of two frozen, off-the-shelf Natural Language Inference (NLI) models and lightweight lexical signals. These features are used to train a simple, calibrated, and task-adapted meta-classifier. Using a rigorous 5-fold out-of-fold (OOF) training protocol to prevent data leakage and produce unbiased estimates, we evaluate our system on the HaluEval benchmark. By pairing our universal feature set with a lightweight, task-adapted classifier and a precision-constrained decision policy, HALT-RAG achieves strong OOF F1-scores of 0.7756, 0.9786, and 0.7391 on the summarization, QA, and dialogue tasks, respectively. The system's well-calibrated probabilities enable a practical abstention mechanism, providing a reliable tool for balancing model performance with safety requirements. |
| title | HALT-RAG: A Task-Adaptable Framework for Hallucination Detection with Calibrated NLI Ensembles and Abstention |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2509.07475 |