fine-tuning-base-model-instruction-data-removing-training-targets-anyWhen fine-tuning a base model on instruction data, removing from the training targets any factual claim the base model cannot consistently recall raises the supported-claim rate of later long-form generations, but the gain comes largely from a more conservative response policy — more refusals and fewer supported claims per answer — not from generating more correct facts at equal coverage.
Ingested from a paper but not yet reviewed by a human. It is deliberately inert: it does not move any technique’s standing, does not count toward the backtest, and is excluded anywhere a claim would carry weight. Read the source before relying on it.
Capability: Stating false facts confidently
Observed on
Shown on Qwen3-4B-Base and OLMo 3 7B fine-tuned on the small English first-turn OASST1 set, evaluated on entity-centric long-form factuality benchmarks (WildHalu, Biography) with a.
Sources
- Compared four knowledge-alignment methods against standard SFT under one training setup, plus an ablation varying only the share of known claims (100/50/0%) with prompt count and refusal count fixed, which is the part that isolates causality. Factuality metrics count refusals as fully supported, so the headline gain is partly definitional; the authors say so and report the falling supported-claim counts. Single dataset, small SFT corpus, automatic verifiers.
Disagreeing is the most useful thing you can do here. Both sides of every contested claim in this catalog were assembled by the same person, which is its weakest point.
Related claims
- When training small instruction-tuned models with reinforcement learning plus factual supervision, routing each atomic fact's verification score only to the tokens that produced it, and down-weighting verifier judgements that do not change when their key evidence is removed, improves factuality benchmark scores over trajectory-level or reasoning- step-level factual rewards.Checking claims against evidence · unreviewed
- For small instruction-tuned models (3-4B) answering closed-form true/false questions under a stated user opinion, scoring each sampled response by how much more common its answer is than the group itself predicted, and using that score as the GRPO reward, reduces answer flips under user pressure and raises accuracy without any labels, roughly matching label-supervised desycophancy fine-tuning at higher compute cost.Telling the user what they want to hear · unreviewed
- In open-weight instruction-tuned models, interventions that suppress caving to user pushback (DPO, SFT on chosen responses, or activation steering) also tend to reduce the model's rate of correcting a wrong answer when genuine supporting evidence is supplied, because the two answer-flip behaviors run on overlapping MLP neurons and attention heads with positively aligned steering directions.Telling the user what they want to hear · unreviewed
- When retrieval for a summarization task pulls definitions by surface term match from a general encyclopedia, ambiguous terms fetch the wrong sense and the model incorporates that unsupported background into its output, lowering claim-level factuality below the no-retrieval baseline even when the prompt tells it to ignore unrelated retrieved content.Stating false facts confidently · unreviewed
- For persistent-memory agents, any memory-write rule that decides using only recency and provenance is stuck on a single tradeoff — accepting more genuine preference updates means admitting more poisoned ones — because an adversary who can launder a claim through the user's own channel matches the statistics a genuine revision produces; conditioning the write decision on the inferred authenticity of the claim given the interaction history moves both axes at once.Remembering across sessions · unreviewed
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 run where recall-filtered targets raise supported-claim percentage while holding refusal count and number of supported claims per response equal to standard SFT would show the gain is not coverage-driven; conversely, showing no factuality gain at all when the share of known claims in targets is varied would falsify the mechanism. Proposed technique, not catalogued: Recall-consistency filtering of fine-tuning targets.