Precise Zero-Shot Dense Retrieval without Relevance Labels · HackerPapers discussions

Precise Zero-Shot Dense Retrieval without Relevance Labels — mentioned by kaycebasques

Fri, 14 Aug 2026 15:54:00 GMT

https://arxiv.org/abs/2212.10496 for others like me hearing about HyDE for the first time

Paper and discussion history. A mention is not an endorsement.

Precise Zero-Shot Dense Retrieval without Relevance Labels — HN submission

Fri, 14 Aug 2026 15:52:36 GMT

Hypothetical Document Embeddings

3 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Precise Zero-Shot Dense Retrieval without Relevance Labels — mentioned by osmarks

Sun, 23 Mar 2025 20:19:11 GMT

https://arxiv.org/abs/2212.10496

Paper and discussion history. A mention is not an endorsement.

Precise Zero-Shot Dense Retrieval without Relevance Labels — HN submission

Fri, 01 Nov 2024 21:03:13 GMT

Hypothetical Document Embeddings (HyDE) for Precise Zero-Shot Retrieval [pdf]

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Precise Zero-Shot Dense Retrieval without Relevance Labels — mentioned by mrshu

Fri, 01 Nov 2024 12:56:21 GMT

This is also often referred to as Hypothetical Document Embeddings (https://arxiv.org/abs/2212.10496).

Paper and discussion history. A mention is not an endorsement.

Precise Zero-Shot Dense Retrieval without Relevance Labels — mentioned by postalcoder

Fri, 20 Sep 2024 07:56:29 GMT

To add some context, this isn't that novel of an approach. A common approach to improve RAG results is to "expand" the underlying chunks using an llm, so as to increase the semantic surface area to match against. You can further improve your results by running query expansion using HyDE[1], though it's not always an improvement. I use it as a fallback. I'm not sure what Anthropic is introducing here. I looked at the cookbook code and it's just showing the process of producing said context, but there's no actual change to their API regarding "contextual retrieval". The one change is prompt…

Paper and discussion history. A mention is not an endorsement.

Precise Zero-Shot Dense Retrieval without Relevance Labels — mentioned by pbronez

Thu, 02 May 2024 23:45:37 GMT

HyDE apparently means “Hypothetical Document Embeddings”, which seems to be a kind of generative query expansion/pre-processing https://arxiv.org/abs/2212.10496 https://github.com/texttron/hyde From the abstract: Given a query, HyDE first zero-shot instructs an instruction-following language model (e.g. InstructGPT) to generate a hypothetical document. The document captures relevance patterns but is unreal and may contain false details. Then, an unsupervised contrastively learned encoder~(e.g. Contriever) encodes the document into an embedding vector. This vector identifies a neighborhood in…

Paper and discussion history. A mention is not an endorsement.

Precise Zero-Shot Dense Retrieval without Relevance Labels — mentioned by avereveard

Thu, 02 May 2024 19:22:01 GMT

I've tried Hyde and seems to work better. had to do it client side tho. asked chatgpt: "write one sentence explanation about this topic: solutions for postgres clustering" which returned "Solutions for PostgreSQL clustering involve implementing methods such as streaming replication or third-party tools like Patroni to manage and distribute database workloads across multiple servers for enhanced performance and fault tolerance." then I searched that: https://hackersearch.net/search?q=Solutions+for+PostgreSQL+c... and results are much better: 1. An overview of distributed Postgres architectures…

Paper and discussion history. A mention is not an endorsement.

Precise Zero-Shot Dense Retrieval without Relevance Labels — mentioned by bayesian_limit

Thu, 28 Dec 2023 18:04:46 GMT

I could not help but notice the Contriever curve is so much higher on y-axis Recall than the other methods (figure 11 in https://arxiv.org/pdf/2307.03172.pdf). Has anyone come across more recent experiments, results, or papers related to this? I'm acquainted with the: - Contriever 2021 paper https://aclanthology.org/2021.eacl-main.74.pdf - Hyde 2022 https://arxiv.org/pdf/2212.10496.pdf My suspicion is some pre-logic such as is the user's question dense enough then use Hyde with chat history. If anyone has more recent experience with Contrievers, would love to learn more about it! Feel free to…

Paper and discussion history. A mention is not an endorsement.

Precise Zero-Shot Dense Retrieval without Relevance Labels — mentioned by hobofan

Wed, 20 Dec 2023 10:59:01 GMT

If you know that your search queries will be actual questions (like in the example you listed), you can possibly use the HyDE[0] to create a hypothetical answer which will usually have an embedding that's closer to the RAG chunks you are looking for. It has the downside that an LLM (rather than just a embedding model) is used in the query path, but it has helped me multiple times in the past to strongly reduce problems with RAG like the ones you outlined, where it likes to latch onto individual words. [0]: https://arxiv.org/abs/2212.10496

Paper and discussion history. A mention is not an endorsement.

Precise Zero-Shot Dense Retrieval without Relevance Labels — mentioned by danielbln

Thu, 14 Sep 2023 13:50:18 GMT

The approach is based on hypothetical document embeddings (HyDE). Here is a good description of it in the context of langchain: https://python.langchain.com/docs/use_cases/question_answeri... The original paper proposing this technique can be found here: https://arxiv.org/pdf/2212.10496.pdf

Paper and discussion history. A mention is not an endorsement.

Precise Zero-Shot Dense Retrieval without Relevance Labels — mentioned by d4rkp4ttern

Tue, 09 May 2023 11:01:57 GMT

Some people packaged this rather intuitive idea, named it Hyde (Hypothetical Document Embeddings) and wrote a paper about it — https://arxiv.org/abs/2212.10496 Summary — HyDE is a new method for creating effective zero-shot dense retrieval systems that generates hypothetical documents based on queries and encodes them using an unsupervised contrastively learned encoder to identify relevant documents. It outperforms state-of-the-art unsupervised dense retrievers and performs strongly compared to fine-tuned retrievers across various tasks and languages.

Paper and discussion history. A mention is not an endorsement.

Precise Zero-Shot Dense Retrieval without Relevance Labels — mentioned by Buoy

Fri, 03 Mar 2023 03:54:59 GMT

Thanks for flagging - will get this fixed! For reference the paper is here: https://arxiv.org/abs/2212.10496

Paper and discussion history. A mention is not an endorsement.

Precise Zero-Shot Dense Retrieval without Relevance Labels — mentioned by curo

Sat, 25 Feb 2023 23:37:46 GMT

Query (→ GPT3 completion) → vector db lookups → GPT3 synthesis The optional step two is used when the lookups are more closely related to an answer's latent space than the original query text. This approach is called HyDE (first published here: https://arxiv.org/abs/2212.10496). The synthesis is also optional. You can essentially summarize your lookups or refine them or do whatever you want at this stage. If you skipped steps 2 and 4, it's just a semantic search engine. If you skip step 2, you're either doing it for latency/performance reasons, or because the user query's embeddings are more…

Paper and discussion history. A mention is not an endorsement.

Precise Zero-Shot Dense Retrieval without Relevance Labels — mentioned by yayr

Sat, 11 Feb 2023 23:43:32 GMT

it is a result of trying to align the AI model after it has been trained using self-supervised learning with an addition human feedback step. OpenAI has a model / process called InstructLM or InstructGPT see e.g. https://arxiv.org/pdf/2212.10496.pdf https://arxiv.org/pdf/2203.02155.pdf also an approach to solve the alignment problem. https://en.wikipedia.org/wiki/AI_alignment

Paper and discussion history. A mention is not an endorsement.

Precise Zero-Shot Dense Retrieval without Relevance Labels — mentioned by simonw

Sun, 29 Jan 2023 18:54:54 GMT

Yeah I'm happy with the results I got from embeddings so far. The areas I want to explore there are: 1. What's the ideal size of text to embed? I'm doing whole blog entries right now but I'm confident I can get better results if I divide them up into smaller chunks first - I'm just not sure how best to do that. 2. There's a trick called Hypothetical Document Embeddings (HyDE) where you ask GPT-3 to invent an answer to the user's question, embed THAT fictional answer, then use that embedding to find relevant documents in your corpus. https://arxiv.org/abs/2212.10496

Paper and discussion history. A mention is not an endorsement.

Precise Zero-Shot Dense Retrieval without Relevance Labels — HN submission

Mon, 23 Jan 2023 20:58:16 GMT

Precise Zero-Shot Dense Retrieval Without Relevance Labels

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Precise Zero-Shot Dense Retrieval without Relevance Labels — mentioned by kerbal

Sun, 22 Jan 2023 17:59:08 GMT

I’ve also used similar approach to build Q&A system for PDF files (my main use case - board game manuals). OpenAIs embeddings are nice to play with. Also there is an easy technique for getting better results with dense search - Hypothetical Document Embeddings (https://arxiv.org/abs/2212.10496).

Paper and discussion history. A mention is not an endorsement.