New guidelines say GenAI still needs human oversight in systematic literature reviews
DrDatta_AIIMS · x · 2026-07-29
A new arXiv paper proposes preliminary guidelines for using and evaluating GenAI in systematic literature reviews (SLRs).
- The authors argue that while LLMs can summarize text, SLRs require rigor, reliability, and transparency that current tools do not guarantee.
- They combine a rapid review, thought experiments, and their own SLR experience to derive process recommendations.
- The paper introduces GUEST: GenAI Use and Evaluation in SLR Tasks, a set of recommendations for planning, conducting, and reporting SLRs with GenAI.
More from Research
- AI Safety Researchers Debate Why Model Goal Guarding Mechanisms Fail — RyanGreenblatt · 2026-07-30
- ITSMBench Released: Benchmarking Enterprise AI Agents on System Actions and Audit Trails — Shahules786 · 2026-07-30
- ITSMBench Released: Frontier Models Struggle with Enterprise Agent Reliability — Shahules786 · 2026-07-30
- Harvey Open-Sources Legal Agent Benchmark Spanning 1,200 Tasks — baseten · 2026-07-30
- DeepMind’s AI co-scientist solved a 10-year bacterial gene-transfer problem in two days — nathanbenaich · 2026-07-30
- AI Moves Too Fast: NAACL 2027 Workshop Proposals Slammed as Outdated — yanaiela · 2026-07-30