open-source-vlms-asked-justify-answers-object-removal-counterfactual-image-pairs CLM-0215For open-source VLMs asked to justify answers on object-removal counterfactual image pairs (A-OKVQA, SNLI-VE), explanations written after the answer is committed (Predict-then-Explain) mention the removed object more in proportion to how much its removal shifts the answer distribution than pre-answer step-by-step CoT does, so pre-answer reasoning is not the more faithful format here.
Capability: Saying what actually drove the answer
Observed on
Eight open-source VLMs (9B-38B), single-object diffusion removal edits, answer distributions restricted to a fixed candidate set, visible prompted explanations with native thinking.
Sources
- Point-biserial correlation between TVD answer shift and LLM-judged mention of the removed object; PE beat CoT in all 16 model-dataset pairs (A-OKVQA mean 0.303 vs 0.200; SNLI-VE 0.264 vs 0.129) with paired permutation p<0.05, and held under accuracy-matched and original-image-only mention controls. Absolute correlations are modest, mention detection is a model judge (92.2% human agreement), edits are correct in ~88-93% of audited cases, and the test is behavioral, not mechanistic.
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
- When vision-language models are given an explicit abstention option plus a stated payoff for correct, wrong and declined answers, quadrupling the penalty for a wrong answer barely changes how often they answer, so their abstention rate is largely insensitive to the stated cost of error across text, synthetic video and natural video recall tasks.Saying it does not know · reviewed by AI
- When an LLM gives an answer plus an explanation, deleting from the input those concepts the explanation does not credit and re-querying on the reduced input raises measured faithfulness over both standard prompting and prompts that ask for faithful explanations, because the re-query removes the unmentioned factors that could have influenced the original answer.Saying what actually drove the answer · reviewed by AI
- For binary visual question answering with open LVLMs (InstructBLIP-7B, Qwen2.5-VL, InternVL-4B), a hallucinated answer can be held with high response consistency, so a single consistency/uncertainty score misses it; separating consistency into four probe groups (image vs. text perturbation crossed with affirmative vs. negated statement) and classifying on the joint within- and between-group agreement pattern detects hallucination better than any single-score black-box or white-box baseline.Stating false facts confidently · reviewed by AI
- On questions whose premises are false or internally contradictory, prompting mid-size instruct models (Qwen2.5-7B, LLaMA-3.1-8B, Gemma3-12B) to reason step by step can lower accuracy below plain answering, because the reasoning chain elaborates from the flawed premise instead of challenging it.Stating false facts confidently · reviewed by AI
- When an LLM answers a question and gives an explanation, removing from the input the concepts its explanation did not credit and re-querying on the reduced input raises measured explanation faithfulness over both standard prompting and prompts that ask for faithfulness, because the removal deletes the unmentioned influences rather than asking the model to report them.Saying what actually drove the answer · 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. Drafter linked technique "chain-of-thought", which does not list this capability in addresses -- recorded, not asserted. Drafted confidence: medium. Falsifier as drafted: A comparable study on visual counterfactuals where pre-answer CoT correlates at least as strongly with intervention-induced probability shifts as post-answer explanations, across multiple models and datasets. Proposed technique, not catalogued: Counterfactual visual faithfulness tests (vCT/vCCT). Automatic check flagged: figures not in the source: 88.