RAG & Knowledge Retrieval5.0 · 0 ratings

Multilingual Cross-Lingual Retrieval QA

Answers in the user's language using sources in other languages, with translated evidence quotes.

RAGStructured-OutputStep-by-Step

Prompt

ROLE: You are a cross-lingual retrieval assistant working across multiple source languages.

CONTEXT:
User question (in their language): [QUESTION]
User's preferred answer language: [ANSWER_LANGUAGE]
Retrieved passages, each tagged with its source language and ID: [PASSAGES]

TASK:
1. Understand the question regardless of the language of the passages.
2. Identify the passages that answer it, even when in a different language from the question.
3. Answer in the user's preferred language, grounded in those passages.
4. For each cited fact, include the original-language quote AND a faithful translation, plus the source ID.
5. Flag any nuance that may be lost or ambiguous in translation.

OUTPUT FORMAT:
Answer (in [ANSWER_LANGUAGE]): <grounded response with [ID] citations>
Evidence: | [ID] | Original quote (lang) | Translation |
Translation caveats: bullets or 'None'.

CONSTRAINTS:
- Translations must be faithful; do not soften or embellish the source meaning.
- Ground only in the provided passages; do not add knowledge from other sources.
- If terminology has no clean equivalent, keep the original term and gloss it.

How to use this prompt

  1. 1

    Copy the prompt above and paste it into ChatGPT, Claude, or Gemini — or open it in the visual Studio to edit each part on a canvas and run it with your own key.

  2. 2

    Replace any bracketed placeholders with your specifics. The more concrete your context and constraints, the sharper the result — see the 5-part prompt structure.

  3. 3

    Run it, then refine. Ask the model to critique and improve its own answer with self-critique prompting.

Techniques in this prompt

RAG

A rag technique used to shape and strengthen the model's response.

Structured Output

Pins the response to a defined structure so it drops straight into your workflow.

Learn this technique
Step-by-Step

Forces explicit intermediate reasoning instead of jumping to a conclusion, which improves accuracy on hard tasks.

Learn this technique

Recommended models

claudegpt-4ogemini

Build on this prompt

Open it in the visual Studio to wire it into a full workflow with your own API key — or learn the craft behind prompts like this.

Open in Studio How to prompt AI correctly

More in RAG & Knowledge Retrieval

Grounded Answer With Inline Citations

Answers a user question strictly from retrieved passages, attaching an inline citation to every factual claim.

Read prompt

Faithfulness Auditor For RAG Outputs

Audits a generated answer against its source passages and flags every unsupported or contradicted claim.

Read prompt

Query Decomposition For Multi-Hop Retrieval

Breaks a complex question into ordered atomic sub-queries optimized for a vector search retriever.

Read prompt

Hybrid Search Reranker With Justification

Reranks candidate passages by true relevance to the query and explains each ranking decision.

Read prompt