{"id":32262,"date":"2026-01-21T17:01:36","date_gmt":"2026-01-21T17:01:36","guid":{"rendered":"https:\/\/lamarr-institute.org\/publication\/explainable-hallucination-through-natural-language-inference-mapping\/"},"modified":"2026-06-08T13:19:03","modified_gmt":"2026-06-08T13:19:03","slug":"explainable-hallucination-through-natural-language-inference-mapping","status":"publish","type":"publication","link":"https:\/\/lamarr-institute.org\/de\/publication\/explainable-hallucination-through-natural-language-inference-mapping\/","title":{"rendered":"Explainable Hallucination through Natural Language Inference Mapping"},"content":{"rendered":"<p>Large language models ({LLMs}) often generate hallucinated content, making it crucial to identify and quantify inconsistencies in their outputs. We introduce {HaluMap}, a post-hoc framework that detects hallucinations by mapping entailment and contradiction relations between source inputs and generated outputs using a natural language inference ({NLI}) model. To improve reliability, we propose a calibration step leveraging intra-text relations to refine predictions. {HaluMap} outperforms state-of-the-art {NLI}-based methods by five percentage points compared to other training-free approaches, while providing clear, interpretable explanations. As a training-free and model-agnostic approach, {HaluMap} offers a practical solution for verifying {LLM} outputs across diverse {NLP} tasks. The resources of this paper are available at https:\/\/github.com\/caisa-lab\/acl25-halumap.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Large language models ({LLMs}) often generate hallucinated content, making it crucial to identify and quantify inconsistencies in their outputs. We introduce {HaluMap}, a post-hoc framework that detects hallucinations by mapping entailment and contradiction relations between source inputs and generated outputs using a natural language inference ({NLI}) model. To improve reliability, we propose a calibration step leveraging intra-text relations to refine predictions. {HaluMap} outperforms state-of-the-art {NLI}-based methods by five percentage points [&hellip;]<\/p>\n","protected":false},"author":12,"featured_media":0,"template":"","meta":{"_acf_changed":false,"footnotes":""},"publication-type":[32],"class_list":["post-32262","publication","type-publication","status-publish","hentry","publication-type-inproceedings"],"acf":[],"publishpress_future_workflow_manual_trigger":{"enabledWorkflows":[]},"_links":{"self":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication\/32262","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication"}],"about":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/types\/publication"}],"author":[{"embeddable":true,"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/users\/12"}],"version-history":[{"count":0,"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication\/32262\/revisions"}],"wp:attachment":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/media?parent=32262"}],"wp:term":[{"taxonomy":"publication-type","embeddable":true,"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication-type?post=32262"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}