training · refusal-aware-instruction-tuning TEC-0058 · proposed

Refusal-aware instruction tuning

Run the base model on the tuning set, label each example as known or unknown by whether it answered correctly, keep answers for the known set and append an uncertainty expression to the unknown set, then fine-tune on the union so the model

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.

Run the base model on the tuning set, label each example as known or unknown by whether it answered correctly, keep answers for the known set and append an uncertainty expression to the unknown set, then fine-tune on the union so the model Filed by the drafting stage from R-Tuning: Instructing Large Language Models to Say `I Don't Know' (2311.09677) 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: AP scores in single-task and multi-task settings against vanilla instruction tuning on the same data, plus out-of-domain AP on HaluEval-QA and a comparison against uncertainty-based filtering at test time; 3B-13B open models only.. Nobody has vouched for it; add support or contest it on this page.

Addresses: Saying it does not know

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

Either way, bring evidence: a link, or what you saw.

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.