Unverified50% confidenceSolutionExact time
HyDE (Hypothetical Document Embeddings) has the model first generate a hypothetical answer, then uses the vector of that text to retrieve real documents, in order to close the semantic gap between the query and the documents.
1
Sources
50%
Confidence
Long-term
Relevance
9/29/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe paper proposes an LLM-as-a-judge external filtering approach, which uses the parametric knowledge of large language models to judge whether transcribed text is contextually plausible and thereby discards contextually implausible transcription results.62% similarUnverifiedWhen a model is responsible for both generating a summary and reading that summary to continue its work, the compression step becomes an attack surface that may be self-exploited.61% similarUnverifiedHaving the model generate skill files based on documentation it has actually read, then using /compact to compress the context, yields development references grounded in real documentation to reduce model errors.60% similarUnverifiedThe paper proposes a framework called "coverage–compression," which abstracts the closed-book question-answering task as a setting of N queries, K answers per query, M facts observed, compressed into at most B bits.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/959353API
curl https://kongchang.com/api/v1/knowledge/claims/959353MCP
get_claim(id=959353)