- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper studies hallucinations in multimodal large language models from the perspective of interactions between visual and linguistic information pathways. The authors challenge the conventional explanation that hallucination primarily arises from insufficient visual grounding or excessive reliance on linguistic priors. Instead, they observe that hallucinated generations can exhibit stronger visual-pathway influence. To explain this behavior, the paper introduces path conflict, defined as a directional inconsistency between the Image-to-Text (I2T) and Text-to-Text (T2T) pathways during token prediction. The authors further propose conflict ratio and conflict strength to quantify the frequency and magnitude of such conflicts at the attention-head level. Based on their analysis, the authors report that hallucinated samples exhibit stronger path conflict, with the difference primarily attributed to increased I2T contributions while T2T contributions remain comparatively stable.
Critical strengths
- The central observation that hallucinated predictions can involve stronger visual influence is counter-intuitive and challenges the commonly adopted insufficient visual grounding explanation. The distinction between pathway strength and pathway directional agreement is conceptually meaningful: two pathways may both contribute strongly while pushing the prediction in opposite directions.
- Rather than introducing an unrelated mitigation technique, the authors use conflict strength to identify conflict-prone heads and independently regulate I2T and T2T flows.
- The definition of path conflict based on the directional inconsistency between I2T and T2T contributions is intuitive and mechanism-oriented.
Critical weaknesses
- The experiments demonstrate a strong association between path conflict and hallucination, but this does not establish that path conflict is a causal source of hallucination. In particular, the observed improvement from intervention could potentially result from simply attenuating strong I2T contributions rather than resolving directional conflict itself. Stronger controlled experiments are needed to distinguish these explanations.
- Both conflict ratio and conflict strength depend on the estimated I2T and T2T pathway contributions. It is therefore important to determine whether the reported conflict phenomenon is intrinsic to the model or partly induced by the specific decomposition/attribution procedure used by the authors. The paper does not provide sufficient evidence using alternative attribution formulations.
- The method requires selecting the top-K conflict heads and choosing separate I2T/T2T scaling coefficients. The reported optimal values may depend on the particular model and benchmarks. The paper does not sufficiently establish whether these parameters transfer across datasets and models or whether they require tuning for each setting.
Questions for authors
- What evidence supports the claim that path conflict is a causal mechanism rather than a consequence or correlate of hallucinated predictions?
- Have the authors compared conflict-strength-based head selection with selecting heads solely according to their I2T contribution magnitude?
- Do the authors have evidence that the observed path conflict phenomenon and the effectiveness of the intervention extend beyond LLaVA-v1.5-7B?