lora-ensemble-credal-commitment-rules-7-9b-instruct-backbones-decision-commit CLM-0607mechanismsingle paperReviewed by AI
For LoRA-ensemble credal commitment rules on 7-9B instruct backbones, the decision to commit tracks agreement among the adapters rather than whether a request should be answered: on AdvBench harmful prompts the ensembles commit more often (33-97%) and with higher lower-bound confidence than on benign Dolly instructions, because safety training makes refusal the unanimous first continuation.
Capability: Saying it does not know
Observed on
Llama-3.1-8B, Gemma-2-9B, Qwen2.5-7B with five CoQA-trained LoRA adapters; 250 harmful vs 250 benign prompts; short-answer settings..
Sources
- Measured on one 250+250 prompt split per backbone, three backbones, with the base model's entropy as comparison (also inverted). Single dataset pair; no variation of safety-training strength, so the mechanism (unanimous refusal continuation) is argued from the pattern rather than isolated.
Either way, bring evidence: a link, or what you saw.
Disagreeing is the most useful thing you can do here. Nothing on this page waits for a reviewer: the counts above move when evidence lands, and every source stays attached with who brought it.
Related claims
- For 7-9B instruct backbones fine-tuned with an ensemble of five LoRA adapters, deciding to answer only when one candidate's minimum probability across adapters exceeds every other candidate's maximum gives a threshold-free abstention rule whose commitment rate collapses when the supplied evidence is corrupted (CoQA 31-48% down to 4-8%), while mean-pooling the same adapters into one distribution requires a tuned threshold and still answers more corrupted prompts at matched clean coverage.Saying it does not know · reviewed by AI
- An abstention rule built from self-consistency, where the model samples several answers and itself scores how many agree with a candidate, can be thresholded by conformal prediction to bound the hallucination rate at a chosen level on closed-book QA; against log-probability confidence it abstains much less often on long-form answers (Temporal Sequences) for the same error bound and matches it on short answers (TriviaQA).Saying it does not know · reviewed by AI
- When an LLM judge must pick the human-preferred response out of more than two candidates, the assumption behind confidence-threshold abstention — that higher estimated confidence means lower disagreement with humans — degrades as the candidate count grows, because probability mass is normalized across more options; restricting the decision to a conformal top-k shortlist and thresholding a margin inside it restores the monotone relation.Saying it does not know · reviewed by AI
- Refusal learned by alignment tuning lives in a low-rank subspace of hidden-state activations that recurs across model families; ablating directions in that subspace lowers harmful-request refusal, and a scalar computed from the subspace's geometry before any fine-tuning (the Geometric Fragility Score) picks out which initially safe model will keep the most refusal after small benign LoRA fine-tuning.Retaining skills and safety after fine-tuning · reviewed by AI
- In closed-book multi-hop QA the accuracy gain from decomposed prompting shrinks to little in frontier models, but answers still change between task-equivalent prompt regimes (agreement only about 70%, and about 60% on MuSiQue), and because stable facts survive re-prompting while hallucinations do not, disagreement across regimes detects errors better than standard uncertainty baselines on F1 and AUROC without retrieval or training.Recalling facts it was trained on · reviewed by AI
Notes
Drafted from the paper by a model and filed unreviewed. Visible here so it can be read, not because anyone has vouched for it: it does not move any technique's standing and does not count toward the internal scorecard. Drafted confidence: medium. Falsifier as drafted: A setup where ensemble commitment rate or lower-bound confidence is lower on harmful prompts than on benign ones, so the commitment signal usefully separates harmful requests in the expected direction.