MétaCan
Menu
Back to cohort
Record W4286903770 · doi:10.48550/arxiv.2110.07752

Hindsight: Posterior-guided training of retrievers for improved\n open-ended generation

2021· preprint· W4286903770 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

aboutThe title or abstract carries a Canadian signal from the geographic lexicon.
no affNo Canadian affiliation: this work is invisible to an affiliation-only frame.
No Canadian affiliation. An affiliation-only frame, the usual design, would never have seen this work. It is one of the works that make the case for inverting the frame.

Bibliographic record

VenuearXiv (Cornell University) · 2021
Typepreprint
Language
FieldComputer Science
TopicTopic Modeling
Canadian institutionsnot available
Fundersnot available
KeywordsHindsight biasComputer scienceContext (archaeology)Generator (circuit theory)Relevance (law)Labrador RetrieverArtificial intelligenceNatural language processingInformation retrievalPsychologyCognitive psychologyMedicinePower (physics)Geography

Abstract

fetched live from OpenAlex

Many text generation systems benefit from using a retriever to retrieve\npassages from a textual knowledge corpus (e.g., Wikipedia) which are then\nprovided as additional context to the generator. For open-ended generation\ntasks (like generating informative utterances in conversations) many varied\npassages may be equally relevant and we find that existing methods that jointly\ntrain the retriever and generator underperform: the retriever may not find\nrelevant passages even amongst the top-10 and hence the generator may not learn\na preference to ground its generated output in them. We propose using an\nadditional guide retriever that is allowed to use the target output and "in\nhindsight" retrieve relevant passages during training. We model the guide\nretriever after the posterior distribution Q of passages given the input and\nthe target output and train it jointly with the standard retriever and the\ngenerator by maximizing the evidence lower bound (ELBo) in expectation over Q.\nFor informative conversations from the Wizard of Wikipedia dataset, with\nposterior-guided training, the retriever finds passages with higher relevance\nin the top-10 (23% relative improvement), the generator's responses are more\ngrounded in the retrieved passage (19% relative improvement) and the end-to-end\nsystem produces better overall output (6.4% relative improvement).\n

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.593
Threshold uncertainty score0.999

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0010.002
Open science0.0050.005
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.256
GPT teacher head0.239
Teacher spread0.017 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it