The paper investigates why supervised fine‑tuning (SFT) of large language models leads to increased hallucinations of factual information. It proposes a self‑distillation SFT approach that regularizes output‑distribution drift to preserve pre‑training knowledge, and shows that freezing parameter groups can reduce hallucinations when new knowledge is unnecessary. Experiments attribute the main cause to interference among overlapping semantic representations, which self‑distillation mitigates, and an associative‑memory model explains the forgetting dynamics.
By Guy Kaplan, Zorik Gekhman, Zhen Zhu, Lotem Rozner, Yuval Reif, Swabha Swayamdipta, Derek Hoiem, Roy Schwartz
ConfRAG introduces a confidence-guided approach to reduce hallucinations in large language models and selectively trigger Retrieval-Augmented Generation (RAG) only when the model is uncertain. The ConfQA fine‑tuning strategy trains the model to answer correctly or respond with "I am unsure," achieving a drop in hallucination rates from 20‑40% to below 5% across factuality benchmarks. Building on ConfQA, ConfRAG limits external retrievals by more than 30% while maintaining over 95% accuracy in ideal scenarios.
By Yin Huang, Yifan Ethan Xu, Kai Sun, Vera Yan, Alicia Sun, Haidar Khan, Jimmy Nguyen, Jingxiang Chen, Mohammad Kachuee, Zhaojiang Lin, Yue Liu, Aaron Colak, Anuj Kumar, Wen-tau Yih, Xin Luna Dong
arXiv:2606. 00919v1 Announce Type: cross Abstract: Large language models (LLMs) have seen widespread adoption across various domains, yet their reliability is frequently undermined by hallucinations - responses that are plausible-sounding but factually incorrect.
By S M Tahmid Siddiqui, Akib Jawad Ononto, Anoop Singhal, Latifur Khan
The paper explores using a language model’s low‑level symbolic skill—specifically SQL—to detect hallucinations without fine‑tuning. By having the model construct an SQL database from reference documents, it can reason over both the source and the model’s output, creating a neurosymbolic check. Experiments on RAGTruth and DiaHalu show this method outperforms direct prediction and rivals state‑of‑the‑art detectors, highlighting the value of leveraging inherent symbolic competences in LLMs.
By Renato Vukovic, Hsien-chin Lin, Carel van Niekerk, Benjamin Ruppik, Michael Heck, Shutong Feng, Nurul Lubis, Milica Gasic
arXiv:2609.15106v1 Announce Type: new
Abstract: Large language models can hallucinate even when the knowledge required for a correct answer is already available. We study this failure through a laten...
By Xuhan Tong, Jiawei Zhang
arXiv:2609.24238v1 Announce Type: new
Abstract: We reproduce and stress-test the work of Yu et al. (2023), who characterize how language models (LMs) arbitrate between memorized knowledge and contrad...
By Guilhem Fouilh\'e, Nicholas Asher, Philippe Muller
arXiv:2605. 31483v1 Announce Type: cross Abstract: Despite Bengali being the sixth most spoken language in the world, no prior work has systematically evaluated hallucination in large language models (LLMs) for Bengali.
By Shefayat E Shams Adib, Ahmed Alfey Sani, Ekramul Alam Esham, Ajwad Abrar, Ishmam Tashdeed, Md Taukir Azam Chowdhury
arXiv:2606. 11105v1 Announce Type: cross Abstract: Hallucinations, where language models (LMs) generate factually ungrounded responses, pose serious risks, as users tend to blindly rely on them.
By Haeji Jung, Hila Gonen
arXiv:2608. 03782v1 Announce Type: new Abstract: Hallucination remains a critical challenge for developing trustworthy Multimodal Large Language Models (MLLMs).
By Ruihan Li, Jiyang Tan, Kailin Jiang, Huining Li, Hengyang Lu, Yu Huang, Qian Li, Yuntao Du
arXiv:2608.30987v1 Announce Type: cross
Abstract: Supervised fine-tuning (SFT) trains a base language model to imitate target responses, and these targets may require knowledge the base model has not...
By Arthur Becker, Jakob Kemmler, David Thulke, Christine Sch\"afer, Christian Dugast, Hermann Ney
arXiv:2603. 09986v3 Announce Type: replace-cross Abstract: Hallucinations, the tendency for large language models to provide responses with factually incorrect and unsupported claims, is a serious problem within natural language processing for which we do not yet have an effective solution to mitigate against.
By Brandon C. Colelough, Davis Bartels, Dina Demner-Fushman
arXiv:2607. 10476v1 Announce Type: cross Abstract: Large language models (LLMs) have emerged as a powerful tool for retrieving knowledge through seamless, human-like interactions.
By Basel Abdeen, S M Tahmid Siddiqui, Meah Tahmeed Ahmed, Anoop Singhal, Latifur Khan, Punya Parag Modi, Ehab Al-Shaer