Line of inquiry
Inquiring lines›What determines success when AI in…›How should research quality be mai…›this line of inquiry
How do LLMs generate false citations that fool readers and evaluators?
A broader line of inquiry — a family of 45 specific questions the research asks around this. Follow one into its inquiring-line page, or move sideways to a related line below.
Questions in this line of inquiry 45
Specific inquiring lines the field asks around this — ordered from the most general framing down to the most specific angle.
- How often do fabricated sources in AI output escape citation checking?
- Can verification mechanisms prevent AI agents from inventing false citations?
- Do citation formatting and numbering fool readers into trusting unreal sources?
- Can citation practices work when AI cannot produce traceable sources?
- How do LLMs generate false citations that sound like real scholarship?
- How susceptible are LLM evaluators to fake references as exploitable biases?
- Why are hallucinated references easier to detect and punish than LLM-assisted writing?
- Can users distinguish between real and fabricated references without checking each one?
- How do retrieval failures enable generation of fabricated scholarly constructs?
- Can AI systems distinguish fabricated papers from legitimate research?
- What safeguards prevent AI from generating fake papers with fabricated citations?
- What happens when lawyers rely on AI citations that turn out false?
- How do courts distinguish between AI hallucinations and ordinary typographical errors?
- How much does citation grounding help if agents ignore the citations?
- Why do users trust citations even when they are irrelevant?
- How do citation errors in AI-generated papers differ from human hallucinations?
- How do entailment checks prevent synthetic data from degrading retrieval corpora?
- Can we verify fabricated text without redesigning the generation process?
- What distinguishes confabulation from honest errors in AI-generated academic content?
- What false positive rate do citation verification tools produce on archival works?
- Do fabricated citations and deception emerge reliably when optimizing for persuasion?
- Can RAG systems game user preferences by adding irrelevant citations?
- Why do citation counts increase trust even without relevance?
- Can lower-quality sources still help readers catch errors despite poor information?
- Why do readers trust citations more even when they are irrelevant?
- How common are undetected AI fabrication errors across Big Four consulting firms?
- What citation mistakes appear in fully autonomous AI research pipelines?
- How often do journal editors catch obvious textual problems before publication?
- Why do longer model outputs correlate with more fabricated claims?
- Does complexity signal credibility and authority to readers?
- How much undetected fraud exists beyond current retraction statistics?
- Should AI platforms be required to cite authoritative government sources?
- Why do users treat one corroborating source as sufficient verification?
- Does provenance alone guarantee that cited sources are actually sound?
- Does performing the source verification work create meaningful engagement with ideas?
- Why are documents read but not cited harder distractors than random samples?
- Do solo lawyers face different citation hallucination risks than large firms?
- Why might opposing counsel catch small firm errors more often?
- Does 'evidence hacking' pose greater risks to politically divisive domains?
- What prevents scholarly infrastructure from filtering out ghost-authored records automatically?
- What role do conference organizers play in accepting problematic articles?
- What linguistic markers distinguish unfalsified corruption from other forms of error?
- How do mirror sites and shadow libraries perpetuate retracted papers?
- Why do fraudulent networks move to different journals after deindexing?
- What standard of intent or bad faith triggers Rule 11 sanctions for citations?