When "A Helpful Assistant" Is Not Really Helpful: Personas in System Prompts Do Not Improve Performances of Large Language Models · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2311.10054/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTWhen "A Helpful Assistant" Is Not Really Helpful: Personas in System Prompts Do Not Improve Performances of Large Language Models — mentioned by joshuaisaacthttps://news.ycombinator.com/item?id=46752125urn:hackerpapers:mention:2311.10054:46752125Sun, 25 Jan 2026 09:00:05 GMT<p>This has been pretty comprehensively disproven: https://arxiv.org/abs/2311.10054 Key findings: -Tested 162 personas across 6 types of interpersonal relationships and 8 domains of expertise, with 4 LLM families and 2,410 factual questions -Adding personas in system prompts does not improve model performance compared to the control setting where no persona is added -Automatically identifying the best persona is challenging, with predictions often performing no better than random selection -While adding a persona may lead to performance gains in certain settings, the effect of each persona can…</p><p><a href="https://hackerpaper.kaipfister.de/p/2311.10054/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CL