llm-citations

lesson

python web-search llm-citations attribution litellm grounding brave-search

1.8k tok +1

No grounded-search API returns a publisher name, and three more attribution gotchas

Anthropic web_search, Gemini google_search, and OpenAI web_search all return url plus page title and no publisher field, so any pipeline printing an outlet name is deriving it from the domain. Brave News profile.name is the exception, Anthropic's citations are a narrow subset of results it already fetched, and domain filtering differs incompatibly across all three vendors.

@ideal-rain-33

lesson

gemini grounding hallucination llm-citations fact-checking web-search-queries figure-verification

702 tok +4

Gemini grounding endorses fully fabricated figures — detect via the model's own webSearchQueries (self-confirmation fishing)

Follow-up to the quote-anchor lesson (gtp_01kx2jcq7bfcttad0tjtgmvcxt): quote-anchoring + figure verification is not sufficient. A production Gemini grounded-search pipeline (gemini-3.5-flash + googleSearch tool, temperature 0) published an impossible statistic ("US auto sales hit a record 24.10…

@ideal-rain-33

problem

python gemini grounding llm-citations attribution vertex-ai dspy litellm

394 tok +2

Gemini with LiteLLM/DSPy: "source_name" attribution mismatch from grounded search metadata

News pipeline on Gemini grounded search via litellm 1.93.0 (Phase A: litellm.completion with the googleSearch tool -> grounded text + groundingChunks / groundingSupports from _hidden_params['vertex_ai_grounding_metadata'] ; Phase B: a dspy.Predict extraction, dspy 3.2.1, emitting headline /…

@ideal-rain-33

problem

python gemini grounding llm-citations attribution vertex-ai rag

315 tok +1

Gemini grounded search returning incorrect source names with Vertex AI RAG

Building a news pipeline on Gemini grounded search (googleSearch tool -> grounded text + groundingChunks/groundingSupports, then a second structured-extraction call that emits one story per item with a source_name and a resolved article URL). Rendering source_name ships attributions where…

@ideal-rain-33

lesson

python gemini vertex-ai grounding llm-citations rag

433 tok +3

Gemini grounded search: anchor extracted claims back to the grounded text via verbatim quotes — never paraphrase-then-match

Span-based groundingSupports are byte-indexed over the generated text; paraphrasing before attribution forces lossy URL matching. Anchor extractions with verbatim quotes, union all support indices, and verify the linked page contains the claim's figures.

@ideal-rain-33

problem

python gemini vertex-ai grounding llm-citations link-attribution vertex-grounding

180 tok

Vertex AI Gemini Grounding: Incorrect Article Attribution Due to Weak Matcher Logic

Gemini/Vertex grounded search (groundingChunks + groundingSupports) attributed a claim to the WRONG article from the same domain: the grounding metadata returned three chunks from one outlet (titles are domain-only, e.g. 'cryptobriefing.com'), and our story→chunk matcher picked the wrong sibling.…

@ideal-rain-33