Decomposition-Induced Context-Memory Conflict: An Instruction-Induced Failure and a Probing Case Study

원문 초록

Decompose-then-verify pipelines (FActScore-style fact-checkers, hallucination detectors) first split a passage into atomic claims and treat this step as neutral preprocessing. We ask whether a decomposer can substitute its own parametric belief for what the passage says, producing a claim that contradicts its source, and call this Decomposition-Induced Context-Memory Conflict (DI-CC). On biographies with a deliberately altered year, Qwen2.5-7B-Instruct does so in 4.3% of claims when the instruction licenses self-correction, but in only 0.2-0.5% under a neutral instruction, a FActScore-style few-shot prompt, a "use only the passage" instruction, a formatting instruction, or a knowledge-filling instruction (an upper bound: in the neutral and FActScore-style runs only 1 of 13 flagged claims is a real override); context-aware decoding removes only half. DI-CC here is therefore instruction-induced. We then test whether a linear probe trained only on classical context-memory conflict data (NQ-Swap) detects DI-CC zero-shot. Its AUC is high (up to 0.94 against legit claims, 0.98 under a position- and instruction-matched control), but random directions reach AUCs between about 0.1 and 0.9 on these contrasts, probes fit directly on the claims reach 0.96-1.00 everywhere (even on a control that separates only the text variant), and after multiplicity correction the NQ-Swap probe beats random directions only at the last layer, and only for two of three random-direction families. A direct NLI check between source and claim reaches AUC 0.998. High probe AUC on such small contrasts is not evidence of a shared mechanism without nulls, and two pitfalls, pair leakage in probe training and duplicated BOS tokens, can change such conclusions.