{"type":"ScholarlyArticle","title":"Directional Hallucinations: Ideological Drift in News-Grounded LLM Question Answering","authors":[{"name":"Chendi Wang","slug":"chendi-wang","given":"Chendi","family":"Wang","affiliation":""},{"name":"Liam Cunningham","slug":"liam-cunningham","given":"Liam","family":"Cunningham","affiliation":""},{"name":"Tom Yishay","slug":"tom-yishay","given":"Tom","family":"Yishay","affiliation":""},{"name":"Jieying Chen","slug":"jieying-chen","given":"Jieying","family":"Chen","affiliation":""}],"abstract":"Large language models (LLMs) are increasingly used to answer questions about political information, including in election-adjacent information settings where factual errors and ideological distortions are high-stakes. We present a reproducible measurement framework that treats hallucinations, unsupported statements in document-grounded QA, as diagnostic signals of ideological drift. Using 21,727 expert-labeled U.S. political news articles from QBias spanning left, center, and right sources, we (i) generate an article-specific question, (ii) elicit document-grounded answers from three open-weight LLMs and one proprietary model, (iii) detect sentence-level hallucinations via reference-based comparison, (iv) classify the ideological valence of hallucinated sentences with a fine-tuned stance classifier, and (v) probe output logits to relate token-level uncertainty to hallucination and drift. Hallucination rates vary substantially across models and concentrate in contentious topics, while source-ideology differences in hallucination frequency are modest. In contrast, hallucination content exhibits robust leftward drift: a majority of hallucinated sentences are classified as left-leaning, including among hallucinations generated from right-leaning sources. Logit-level analysis shows hallucinations arise in high-entropy generation contexts, and in some models uncertainty also predicts leftward drift, consistent with an \"uncertainty → guessing\" mechanism. We discuss implications for auditing AI-mediated political information and for designing safeguards in election-relevant deployments.","doi":"10.24963/ijcai.2026/831","url":"https://ijcai.org/proceedings/2026/831","pdf":"https://ijcai.org/proceedings/2026/0831.pdf","markdown":"https://ijcai.org/proceedings/2026/831.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/831","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"AI and Social Good","track":"AI and Social Good","number":831,"pages":{"first":7474,"last":7482},"keywords":["Uncertainty in AI: Uncertainty in AI","Natural Language Processing: Natural Language Processing","Multidisciplinary Topics and Applications: Multidisciplinary Topics and Applications","AI Ethics, Trust, Fairness: AI Ethics, Trust, Fairness"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}