Hallucination and factual inaccuracy are the shared motivation for grounding LLMs across this body of work: Akari et al. 2023 blame errors on sole reliance on parametric knowledge, Matsumoto et al. 2024 cite hallucinated or irrelevant content and noisy data, and Sušnjak et al. 2025 explicitly design hallucination-mitigation solutions.
E2 attributes factual inaccuracies to LLMs' sole reliance on parametric knowledge, E16 cites hallucinating false or irrelevant information and noisy data, and E9 explicitly proposes solutions for mitigating LLM hallucination, supporting hallucination/factual inaccuracy as the shared motivation across the three works.
Written by Kimi K3 via Ollama Cloud · checked by GLM-5.3 via Ollama Cloud · 1 Oct, 04:39
Source chain
AEvery quote below was checked, without a model, to appear verbatim in its source.
- 01
“large language models (LLMs) often produce responses containing factual inaccuracies due to their sole reliance on the parametric knowledge they encapsulate”
Full-text passage · p. 1 · evidence E2
Preprint. SELF -RAG: L EARNING TO RETRIEVE , G ENERATE , AND CRITIQUE THROUGH SELF -R EFLECTION Akari Asai†, Zeqiu Wu†, Yizhong Wang†§, Avirup Sil‡, Hannaneh Hajishirzi†§ †University of Washington §Allen Institute for AI ‡IBM Research AI {akari,zeqiuwu,yizhongw,hannaneh}@cs.washington.edu, avi@us.ibm.com ABSTRACT Despite their remarkable capabilities, large language models (LLMs) often produce responses containing factual inaccuracies due to their sole reliance on the parametric knowledge they encapsulate. Retrieval-Augmented Generation (RAG), an ad hoc approach that augments LMs with retrieval of relevant knowledge, decreases such issues. However, indiscriminately retrieving and incorporating a fixed number of retrieved passages, regardless of whether retrieval is necessary, or passages are relevant, diminishes LM versatility or can lead to unhelpful response generation. We introduce a new framework called Self-Reflective Retrieval-Augmented Generation (SELF -R AG) that enhances an LM’s quality and factuality through retrieval and self-reflection.
Passage read from arxiv.org, which may be a preprint rather than the published version.
- 02
“LLMs often suffer from some major limitations, such as hallucinating false or irrelevant information, or being influenced by noisy data”
Full-text passage · no page number · evidence E16
Passage read from www.ebi.ac.uk, which may be a preprint rather than the published version.
- 03
“Our research proposed solutions for mitigating LLM hallucination and proposed mechanisms for tracking LLM responses to their sources of information”
Abstract · no page number · evidence E9