Semantic Alignment
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Shared Semantics, Divergent Mechanisms: Unsupervised Feature Discovery by Aligning Semantics and Mechanisms
Announce Type: new Abstract: As large language models are increasingly deployed in high-stakes settings, there is a growing need for tools that audit not only model outputs but also the internal computations that produce them. Circuit analysis is a central approach in mechanistic interpretability, but it is typically target-conditioned, explaining a single prompt paired with a chosen completion. This target-conditioned setup can obscure heterogeneity across a model's continuation distribution.
Grounded but Misleading: Evaluating Semantic Alignment in AI-Generated Security Explanations
arXiv:2602.05056v2 Announce Type: replace Abstract: Online scams increasingly leverage fluent and context-aware social engineering strategies, creating growing demand for AI systems that explain why a message may be risky. However, explanations that cite detector-derived evidence may still semantically weaken or redirect the intended risk interpretation. We introduce VEXA: Verifying Semantic Explanation Alignment, a controlled testbed for studying the gap between lexical grounding and...
SAILRec: Steering LLM Attention to Dual-Side Semantically Aligned Collaborative Embeddings for Recommendation
arXiv:2606.04514v1 Announce Type: new Abstract: 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...
Interpretability in Deep Time Series Models Demands Semantic Alignment
Announce Type: replace Abstract: Deep time series models continue to improve predictive performance, yet their deployment remains limited by their black-box nature. In response, existing interpretability approaches in the field keep focusing on explaining the internal model computations, without addressing whether they align or not with how a human would reason about the studied phenomenon.
SemDINO: A DINOv3-Driven Network for Cross-Temporal Semantic Alignment in Change Detection
arXiv:2606.09772v1 Announce Type: new Abstract: Semantic change detection (SCD) aims to simultaneously locate land-cover changes and identify semantic categories before and after transition. However, existing methods suffer from insufficient cross-temporal alignment, weak multi-scale representation, and poor robustness to pseudo-changes caused by illumination, season, and registration noise. To address these issues, we propose a novel end-to-end semantic change detection network named...
Causal Semantic Alignment for LLM-based Time Series Forecasting
arXiv:2606.08262v1 Announce Type: new Abstract: Recent advances in Large Language Models (LLMs) have opened new possibilities for time series forecasting by enabling alignment between temporal patterns and pretrained word embeddings. However, most LLM-based methods overlook the heterogeneous nature of time series, where dynamic fluctuations and invariant semantics are entangled. This entanglement introduces spurious correlations during the alignment, as dynamic components act as confounders...
Learning Concepts, Not Tokens: Self-Supervised Semantic Alignment for Language Models
arXiv:2603.29123v3 Announce Type: replace Abstract: The next-token prediction (NTP) objective trains language models to predict a single token at each step, even though many continuations can express the same meaning. For example, in the sentence ``this sticker can be placed here'', positioned, attached, or put are all plausible alternatives. While standard NTP training treats these alternatives as mutually exclusive targets, we explore a self-supervised framework that encourages models to...
Segment-driven Structural Induction and Semantic Alignment for Heterogeneous Tabular Representation
arXiv:2606.01890v1 Announce Type: new Abstract: Real-world domains often contain heterogeneous tables whose headers vary while their underlying attribute semantics are shared, making it difficult to induce domain-specialized semantics from table-local evidence alone. Existing encoders model parts of this problem, but often underuse column-level value distributions and apply uniform objectives across attributes with different semantic roles. We propose NAVI, a segment-centric pretraining...
Uncertainty-Aware Hierarchical Re-Localization in OpenStreetMap via Semantic Alignment
arXiv:2603.01613v2 Announce Type: replace Abstract: Monocular re-localization enables robots to estimate camera poses from visual observations. However, many existing methods rely on dense maps or large reference image databases, which face scalability limitations and privacy risks. OpenStreetMap (OSM), as a lightweight privacy-preserving map, offers semantic and geometric information with global scalability.
Native3D: End-to-End 3D Scene Generation via Unified Mesh-Texture Modeling and Semantic Alignment
Announce Type: new Abstract: This paper presents Native3D, the first end-to-end 3D scene generation framework that completely bypasses 2D intermediate representations. Traditional approaches typically require adapting 3D representations to the 2D domain to leverage pre-trained diffusion models, which inevitably introduces domain adaptation issues including geometric structural distortion and texture detail degradation. To address these limitations, we design a unified mesh-texture joint...