- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 1
- Soundness
- 1
Read review
Paper summary
Multimodal models can recognise objects when answering multiple-choice questions, but are unable to mention the same object when asked to describe an image. This paper argues that this is related to differences in the model’s internal computational mechanisms resulting from the differing task instructions. To investigate this issue, the paper designed an ‘Activation Transplantation’ experiment across three models. The results demonstrate differences in the ability to reconstruct images between multiple-choice tasks and free generation. The paper also designed another set of experiments to demonstrate the differences between the two task instructions by removing the attention to the image tokens after prefilling. The paper defines this phenomenon and its explanation as ‘Causal Readout Dependence’: an internal intervention may have a significant impact under one readout condition, while having a lesser impact under another. A broader lesson is that causal effects across different tasks are likely to be inconsistent; therefore, hallucination mitigation methods effective in a specific task context should not be directly transferred.
Critical strengths
The research raises a very good scientific question. The phenomenon observed is interesting.
Critical weaknesses
(1) The scientific question raised in the paper is: ‘Multimodal models are able to recognise objects when answering multiple-choice questions, but are unable to mention the same object when asked to describe an image.’ This is a good question. However, there is a lack of correspondence between the experiments and the motivation. Evidence:
- The conclusions drawn from the main experiment based on the THINGS dataset do not address this question, nor do the explanations provided in the paper fully account for this phenomenon.
- The analysis based on the COCO dataset focuses more on the issue of hallucinations, and the authors also acknowledge that the results do not yet fully explain the POPE-CHAIR disagreement.
(2) The main experiment did indeed observe low recovery in generation position. However, it cannot yet be conclusively demonstrated that this result is due to the cause stated in the paper rather than other factors in the experiment. Evidence:
- There may be confusion between the ‘prompt’ and ‘readout’ factors. ‘Forced choice’ and ‘generation’ differ not only in terms of readout, but also in whether the prompt and answer are explicitly presented, as well as in the donor hidden states that are extracted.
- The introduction of grey images may have an impact. The recipient does not actually lack visual input; rather, it is fed a grey image; its visual tokens, KV cache and so on are not replaced alongside the hidden states; consequently, the generation may still be influenced by that visual context.
- The technical robustness of ‘generation-position recovery’ is questionable. The authors have demonstrated that whether the transplant covers the scored position can increase the open vocabulary recovery rate from near zero to over 70–80 percent. Therefore, it is necessary to verify more directly that the low recovery in generation positions is not caused by information propagation or the conditions under which the intervention covers the position.
Questions for authors
I would like the author to provide clearer and more robust evidence, as well as to improve the writing and the way in which the evidence is presented.
Given the lack of response from the reviewer during the rebuttal period, I am revising my final score to 1 (Reject).