Multimodal large language models (MLLMs) remain prone to visual hallucinations when correct responses depend on subtle visual details. One line of post-training methods constructs visual contrasts through image retrieval, generation, or editing to improve fine-grained perception. However, these contrasts are not built around the model's own hallucinations, making it difficult to ensure that supervision targets its actual perceptual confusions. Another line suppresses hallucinated outputs through response correction or preference learning under fixed image conditions, but leaves the design of supervision signals on the image-input side underexplored. Inspired by how humans correct misconceptions, we introduce DreamRealm, a post-training framework that explores diverse latent hallucinated responses, minimally edits original images to make them valid, and trains the model to assign each response to its supporting image. Our data construction pipeline, RealmForgePipe, mines observed and latent hallucinations from a target model and materializes them through image editing. Using hallucinations mined from Qwen3.5-9B, we construct the Realized Hallucination Dataset (RealmSet). Our training objective, RealmMatch, constructs a likelihood score matrix across image--response combinations and combines supervised learning with bidirectional contrastive losses to reinforce correct matches and suppress mismatches. Compared with the original Qwen3.5-9B model, DreamRealm improves performance across six visual perception and hallucination benchmarks, including gains of 7.26 percentage points in HallusionBench accuracy and 11.34 percentage points in MMVP pair accuracy. Together with ablation studies on data construction and training methods, these results demonstrate that hallucination assignment is a promising paradigm for improving visual perception and mitigating hallucinations.
Haolei Xu Zhejiang University, Haiwen Hong Alibaba Group, Hongxing Li, Rui Zhou, Yang Zhang, Longtao Huang Alibaba Group, Hui Xue, Yongliang Shen Zhejiang University 等 10 位作者
Multimodal Mixture-of-Experts (MoE) models have achieved remarkable performance on vision-language tasks. However, we identify a puzzling phenomenon termed Seeing but Not Thinking: models accurately perceive image content yet fail in subsequent reasoning, while correctly solving identical problems presented as pure text. Through systematic analysis, we first verify that cross-modal semantic sharing exists in MoE architectures, ruling out semantic alignment failure as the sole explanation. We then reveal that visual experts and domain experts exhibit layer-wise separation, with image inputs inducing significant routing divergence from text inputs in middle layers where domain experts concentrate. Based on these findings, we propose the Routing Distraction hypothesis: when processing visual inputs, the routing mechanism fails to adequately activate task-relevant reasoning experts. To validate this hypothesis, we design a routing-guided intervention method that enhances domain expert activation. Experiments on three multimodal MoE models across six benchmarks demonstrate consistent improvements, with gains of up to 3.17% on complex visual reasoning tasks. Our analysis further reveals that domain expert identification locates cognitive functions rather than sample-specific solutions, enabling effective transfer across tasks with different information structures.
尚无 AI 解读，展示原文摘要
cs.CL · cs.CV
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Large Language Models (LLMs) are increasingly deployed in socially sensitive domains, yet their unpredictable behaviors, ranging from misaligned intent to inconsistent personality, pose significant risks. We introduce SteerEval, a hierarchical benchmark for evaluating LLM controllability across three domains: language features, sentiment, and personality. Each domain is structured into three specification levels: L1 (what to express), L2 (how to express), and L3 (how to instantiate), connecting high-level behavioral intent to concrete textual output. Using SteerBench, we systematically evaluate contemporary steering methods, revealing that control often degrades at finer-grained levels. Our benchmark offers a principled and interpretable framework for safe and controllable LLM behavior, serving as a foundation for future research.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Ziwen Xu Zhejiang University, Chenyan WU Zhejiang University of Technology, Hengyu Sun, Haiwen Hong Alibaba Group, Mengru Wang, Yunzhi Yao Zhejiang University, Longtao Huang Alibaba Group, Hui Xue 等 12 位作者
Methods for controlling large language models (LLMs), including local weight fine-tuning, LoRA-based adaptation, and activation-based interventions, are often studied in isolation, obscuring their connections and making comparison difficult. In this work, we present a unified view that frames these interventions as dynamic weight updates induced by a control signal, placing them within a single conceptual framework. Building on this view, we propose a unified preference-utility analysis that separates control effects into preference, defined as the tendency toward a target concept, and utility, defined as coherent and task-valid generation, and measures both on a shared log-odds scale using polarity-paired contrastive examples. Across methods, we observe a consistent trade-off between preference and utility: stronger control increases preference while predictably reducing utility. We further explain this behavior through an activation manifold perspective, in which control shifts representations along target-concept directions to enhance preference, while utility declines primarily when interventions push representations off the model’s valid-generation manifold. Finally, we introduce a new steering approach guided by this analysis that improves preference while better preserving utility.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表