19 articles mentioning Salience-1.5-Pro
arXiv:2610.19387v1 Announce Type: new Abstract: Identification and ranking of salient propositions in documents is indirectly involved in many AI tasks, but few papers define proposition salience scores clearly, make diverse data available, or evaluate models directly on the task. This paper propose
arXiv:2610.00233v1 Announce Type: cross Abstract: When an informed adversary shares the audience of a constrained signalling channel, the signal that best protects the truth is the signal that best describes it. On 108 confirmatory items, the adversary-robust optimum aligns exactly with the salience
arXiv:2609.31130v1 Announce Type: new Abstract: We empirically investigate Question Under Discussion based modelling in naturalistic dialogue by studying whether the salience of generated potential questions predicts their subsequent resolution. Building on Wu et al. (2024), we construct a dataset o
arXiv:2607.12500v2 Announce Type: replace Abstract: Deep learning models for online handwriting recognition have been shown effective and are increasingly deployed in practical applications. However, their vulnerability to adversarial attacks is still a challenge. Existing adversarial methods are pr
arXiv:2607.17486v2 Announce Type: replace-cross Abstract: As large language models (LLMs) process increasingly longer prompts, computation and KV-cache memory costs have emerged as major bottlenecks in inference systems. Existing input-level prompt compression methods address this, but rank each sen
arXiv:2607.27591v1 Announce Type: cross Abstract: Feed-forward networks (FFNs) dominate memory traffic and computation in large language model (LLM) inference, making them a primary target for activation sparsification. However, existing training-free methods suffer substantial model-quality degrada
arXiv:2607.28478v1 Announce Type: new Abstract: As large language models (LLMs) continue to advance in complex reasoning tasks, they have learned to heavily prioritize explicit conditions provided in the input. However, in everyday commonsense reasoning, this mechanism exposes a critical vulnerabili
arXiv:2607.17535v1 Announce Type: cross Abstract: Agentic retrieval-augmented generation (RAG) systems increasingly retrieve external evidence and orchestrate tools for knowledge-intensive applications. In Multi-Hop question answering, agents chain facts across documents. Existing defenses focus on
arXiv:2606.30395v1 Announce Type: cross Abstract: Consumer confidence is typically modeled as a persistent macroeconomic index, yet its movements arise from households that interpret economic information through heterogeneous constraints, exposures, prior beliefs, and attention. We introduce Consume
arXiv:2606.11654v2 Announce Type: replace-cross Abstract: A social highlighter's most useful signal -- which passages a crowd of readers marks -- exists only for documents people have already read. Can the aggregate crowd salience of a document be predicted from its text before its marks accumulate?
arXiv:2606.10398v1 Announce Type: cross Abstract: Does personalizing what a reader sees pay off, and where does it stop? Using a social web highlighter and a co-readership identity control (the same document highlighted by many users, which holds document and topic fixed and asks whether a person's
arXiv:2606.02158v1 Announce Type: new Abstract: AI-generated text increasingly blends with human writing, raising practical risks such as misinformation, academic misuse, and corpora contamination. While statistical detectors are appealing for efficiency and generalization, they suffer from two key
arXiv:2606.00369v1 Announce Type: cross Abstract: Safe global deployment of AI models requires alignment with human values that vary across cultures. Yet rater pools in safety evaluation datasets remain largely geographically homogeneous, failing to capture geo-cultural differences. Further, it rema
arXiv:2602.19612v5 Announce Type: replace Abstract: Machine Unlearning (MU) enables Large Language Models (LLMs) to remove unsafe or outdated information. However, existing work assumes that all facts are equally forgettable and largely ignores whether the forgotten knowledge originates from pretrai
arXiv:2605.27465v1 Announce Type: cross Abstract: The quadratic cost of self-attention in Vision Transformers (ViTs) constitutes a fundamental bottleneck for practical deployment, motivating a vibrant line of research on token reduction. Among existing approaches, token merging (ToMe) has emerged as
arXiv:2605.21842v1 Announce Type: cross Abstract: Standard transformer attention computes pairwise similarity between queries and keys, treating all tokens as equally salient regardless of their intrinsic informational content. In turbulent fluid dynamics, coherent structures -- the energetically do
arXiv:2605.13651v1 Announce Type: cross Abstract: Audio provides critical situational cues, yet current Audio Language Models (ALMs) face an attention bottleneck in long-form recordings where dominant background patterns can dilute rare, salient events. We introduce NAACA, a training-free NeuroAudit
arXiv:2605.08315v1 Announce Type: new Abstract: Existing LLM-based policy optimizers see only scalar rewards: that a policy scored 0.45, but not whether the agent got stuck in a loop, fell into a hole on the third step, or performed well on 19 out of 20 rollouts and failed catastrophically on one. W
arXiv:2512.12688v3 Announce Type: replace-cross Abstract: Prompt engineering is widely used to shape large language model behavior, yet it is often treated as a practical heuristic rather than as a form of natural-language control. This paper develops a cognitive-semantic account in which prompts fu