Diagnosing Knowledge Conflict in Multimodal Long-Chain Reasoning
Multimodal large language models (MLLMs) in long chain-of-thought reasoning often fail when different knowledge sources provide conflicting signals. We formalize these failures under a unified notion of knowledge conflict, distinguishing input-level objective conflict from process-level effective conflict. Through probing internal representations, we reveal that: (I) Linear Separability: different conflict types are explicitly encoded as linearly separable features rather than entangled; (II) Depth Localization: conflict signals concentrate in mid-to-late layers, indicating a distinct processing stage for conflict encoding; (III) Hierarchical Consistency: aggregating noisy token-level signals along trajectories robustly recovers input-level conflict types; and (IV) Directional Asymmetry: reinforcing the model's implicit source preference under conflict is far easier than enforcing the opposite source. Our findings provide a mechanism-level view of multimodal reasoning under knowledge conflict and enable principled diagnosis and control of long-CoT failures.
Code (0)
등록된 구현이 없습니다.
Tasks
Multimodal ReasoningSimilar Papers 제목 키워드 기반
BRIDGE: Benchmark for multi-hop Reasoning In long multimodal Documents with Grounded Evidence
Multi-hop question answering (QA) is widely used to evaluate the reasoning capabilities of large language models, yet most benchmarks focus on final answer correctness and overlook intermediate reasoning, especially in l…
Multi-hop Question AnsweringCrossCheck-Bench: Diagnosing Compositional Failures in Multimodal Conflict Resolution
Multimodal Large Language Models are primarily trained and evaluated on aligned image-text pairs, which leaves their ability to detect and resolve real-world inconsistencies largely unexplored. In open-domain application…
Multimodal ReasoningBenchmarking Multimodal Knowledge Conflict for Large Multimodal Models
Large Multimodal Models(LMMs) face notable challenges when encountering multimodal knowledge conflicts, particularly under retrieval-augmented generation(RAG) frameworks where the contextual information from external sou…
BenchmarkingRAGRetrieval-augmented GenerationSCoRE: Benchmarking Long-Chain Reasoning in Commonsense Scenarios
Currently, long-chain reasoning remains a key challenge for large language models (LLMs) because natural texts lack sufficient explicit reasoning data. However, existing benchmarks suffer from limitations such as narrow …
BenchmarkingDiagnosticLogical ReasoningMultiple-choiceGetting Sick After Seeing a Doctor? Diagnosing and Mitigating Knowledge Conflicts in Event Temporal Reasoning
Event temporal reasoning aims at identifying the temporal relations between two or more events from narratives. However, knowledge conflicts arise when there is a mismatch between the actual temporal relations of events …
counterfactualData AugmentationHallucinationIn-Context Learning