A large document explains how to read its tables near the front. The tables themselves are dozens of pages later. Both parts get indexed. The LLM can't read the table as it isn't aware of the table instructions.
Below is an example chunk from a table row. In this example the table is a 'inspection schedule' which gives a part, an interval, and a one-letter code. The code is 'R', but the LLM has no way to understand what this means without the table key to interpret it.
Subsystem Inspection Schedule Subsystem: Attitude thruster valve seals Interval: 4,000 operating hours Basis: R
What can the LLM interpret from this table row?
For the attitude thruster valve seal inspection, what does a Basis of R mean?
NOT IN CONTEXT
The letter R is described in the key: The key which explains R is in the introduction of the document, That section is indexed too. It came back 13th.
With the instructions on how to read table data within the introduction and the table in the middle of the document, the LLM can't understand the table rows when they are retrieved. Search returns a ranked list, not a set of related things. So the way to solve this is to enrich each table found in the document with the key found in the introduction.
RANK - What the search scored
1st
the row came back at rank 1 of 2,967
Unchanged by either control.
LLM answer
NOT IN CONTEXT
The introduction is rank 13, so it didn't come back.
What the first chunk held
Subsystem Inspection Schedule Subsystem: Attitude thruster valve seals Interval: 4,000 operating hours Basis: R
You may have moved the slider and experienced nothing. This can be the experience for someone knew to RAG, they increase the number of results and nothing changes.
The fix: enrich each row as you chunk the document. Copy the part of the key that the table row actually uses into the rows chunk, so the model can read it wherever it turns up. The key becomes part of the data.
It refuses rather than guessing what R means, which is the safe way to fail. If a user is confidently provided an incorrect answer by the LLM, then that's dangerous.
Worth contrasting with Lost in the middle, where the same model cheerfully supplied a number of its own rather than admit it hadn't found one. The difference is whether it has an opinion to fall back on. Nobody has a prior belief about what R means in someone's maintenance schedule.
The schedule, the part names, the codes and the figures are all invented, and no material from the real system this is drawn from appears here. The invented handbook is 19 passages, searched alongside 2,948 real ones from this site's corpus so the ranking is measured against genuine competition. Answered by glm-5.2:cloud.