Recent LLM-based recommenders enhance language models with collaborative embeddings from user-item interactions, but making such embeddings available does not ensure their proper use during inference. Through a diagnostic attention analysis, we find that the utilization of collaborative embeddings is depth-dependent and alignment-sensitive, suggesting that LLMs need to balance their internal semantic knowledge with external collaborative knowledge. To address this issue, we propose SAILRec, an LLM-based recommender that improves this balance through dual-side semantic alignment and hierarchical attention steering. The former aligns item-side embeddings with item-text semantics and user-side embeddings with codebook-based semantic profiles, while the latter suppresses premature shallow-layer collaborative interference and strengthens collaborative evidence in deeper decision layers. Experiments on MovieLens-1M and Amazon-Book show that SAILRec consistently outperforms representative baselines, with ablation and masking analyses validating its key designs. Our implementation is available at https://github.com/XuPhoenixyear/SAILRec.

Audio-language models (ALMs) often follow text that conflicts with audio, even when the audio evidence is clear. This behavior leaves an important question unresolved: is the audio-supported answer unavailable, or is it represented but overridden by the conflicting text? We test this question with a same-audio counterfactual that keeps the audio fixed, removes only the conflicting text, and measures the resulting shift in model preference. Across five ALMs and four conflict tasks, 64.1% of conflict samples exhibit a sign flip: the same-audio branch prefers the audio-supported answer, whereas the joint branch prefers the text-supported answer. This pattern suggests that the relevant audio evidence is encoded but loses during arbitration. Activation patching further localizes the reversal to answer-position computation, and patching effects closely track output candidate-score differences (Spearman ρ=0.93). Based on this diagnostic, we propose Gated Audio Counterfactual Logit Correction (GACL), a training-free decoding rule that interpolates between joint and same-audio scores. Under a strict 5 pp faithfulness-drop budget, GACL improves nAUC by 17.8 points over the best contrastive baseline and transfers without retuning to vision-text arbitration (up to +40.5 pp).