repair-one-hop-gaps-add-same-chunk-context TEC-0170 · proposedRepair one-hop gaps and add same-chunk context before RL
Augments each KG triple with same-source-chunk supporting triples for supervision, then uses LLM judges to separate noisy triples from genuine one-hop knowledge gaps, continually fine-tunes on targeted repair items weighted by failure histo
Proposed. Filed by the drafting stage because a paper introduces or tests it. Nobody has vouched for it. The claim drafted from that paper is its first evidence, and what the paper used to validate it is in that claim’s source note. Say whether it held up for you, below.
Augments each KG triple with same-source-chunk supporting triples for supervision, then uses LLM judges to separate noisy triples from genuine one-hop knowledge gaps, continually fine-tunes on targeted repair items weighted by failure histo Filed by the drafting stage from Repair Before Reinforce: Context-Augmented Knowledge Graph Reasoning for Multi-Hop Question Answering (2609.12230) with status proposed: the paper introduces or tests it, and the claim drafted from the paper is its first evidence. The paper validated it by: Accuracy on 8,000 generated 3-hop, 4-hop and 5-hop QA items per setting, across two disease KGs, comparing KG-grounded vs context-grounded supervision and RL from repaired vs unrepaired SFT checkpoints, plus an answer-option shuffling robustness check.. Nobody has vouched for it; add support or contest it on this page.
Does it work?
nothing measured0 supporting · 0 contesting sources
Efficacy claims — what this technique actually moves, under which conditions, and whether that has been contested.
No efficacy claim filed yet. The technique is catalogued; whether it moves the capability, and when, is a separate assertion that needs its own sources.
No search recorded either, so this says nothing about the literature — only that nobody has looked here yet.
Code
No repository linked yet. Contribute one.
Sources
Whether a technique works is a claim. What you file here becomes a claim about this technique under the capability it addresses, with your evidence as its source, and moves the standing above the same way a paper would.