arXiv (All)
open access
One Turn Too Late: Learning When to Intervene Against Multi-Turn Malicious Intent
Hidden malicious intent in multi-turn dialogue poses a growing threat to deployed large language models (LLMs). Rather than exposing a harmful objective in a single prompt, attackers can distribute their intent across multiple benign-looking turns, making defense a problem not only of whether a dial
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- FIGS: Evaluating Multi-Turn Sycophancy Without Penalizing Empathy#1145030
- Conduct Under Pressure: What Sixty Language Models Do When a User Pushes#1061087
- First Make It Playable, Then Make It Good: Staged Interaction Learning for Small Dialogue-Game Agents#780971
- First Make It Playable, Then Make It Good: Staged Interaction Learning for Small Dialogue-Game Agents#779596
- Benchmarking Argumentative Behaviour of LLMs: A Study of Defences Against Character Attacks#1076329
Record · ID 1128585
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive