paperarXivTrust 82 · PrimaryPublished 3d agoLive · 2d ago

When the Database Fails: Prompting LLM Dialogue Agents for Safe Recovery in Task-Oriented Dialogue

Large language models used in task-oriented dialogue often produce fluent but unsafe responses when backend database calls fail, return empty results, or surface mismatched information, inventing venues, confirmations, or booking details not grounded in the database. We study a lightweight prompting-based recovery approach that improves robustness without retraining or additional model calls. We compare three response strategies, including a guided recovery prompt conditioned on structured database status, across six open-weight model families (DeepSeek-R1, Gemma-2, Llama-3, Mistral, Phi-3, an

Lineage graph

Paper → model → repo connections mined from source citations (Tier-1 exact match).

Covers

newsEvaluating long-term memory limits in stateless LLM chatbots — feedback needed [D]newsPrompt injection is exploiting enterprise AI's biggest design flaws by targeting agents, RAG pipelines and model routers newsIEEE Rolls Out Large Language Models Virtual Training Course

Covers (incoming)

newsA system-level approach to prompt injection: separating instruction and data channels in LLM agents [P]

Related across the graph

newsPrompt injection is exploiting enterprise AI's biggest design flaws by targeting agents, RAG pipelines and model routers newsEvaluating long-term memory limits in stateless LLM chatbots — feedback needed [D]newsIEEE Rolls Out Large Language Models Virtual Training Course newsA system-level approach to prompt injection: separating instruction and data channels in LLM agents [P]

Topics

cs.CL