搜索结果：ReFrame

Large language models often struggle with sensitive prompts. They may refuse outright, provide generic safety boilerplate, or fail to address the user's legitimate informational needs that can be answered safely. We introduce SHARD, a self-reframing distillation method to improve safe-helpfulness. It first rewrites sensitive prompts to surface benign intent using philosophical guidelines, then reframes its original responses into safe, more helpful ones, and finally fine-tunes the model on its self-reframed responses. Across DNA and the English subset of LINGUASAFE, SHARD improves helpfulness for most model families while preserving safety. It also remains competitive with distillation from a larger teacher model, suggesting that models can internalize safe and helpful behavior elicited from their own. Warning: This paper contains content that may be offensive or harmful.

Toric quasifolds are nonrational generalizations of toric manifolds and orbifolds. We introduce the notion of nonrationality degree, an invariant that measures the extent to which a toric quasifold fails to be Hausdorff. We do so by first defining analogous notions for the underlying quasilattice and the corresponding quasitorus. We conclude by applying the nonrationality degree to reframe Gordan's lemma in the nonrational setting.

Existing computer-use agents remain fundamentally limited in professional software manipulation: GUI-based agents suffer from fragile visual grounding and long-horizon error accumulation, while API-basedapproaches struggle with heterogeneous protocols and inaccessible commercial interfaces. In this work,we identify the Component Object Model (COM) as a unified executable abstraction, proposing COM-as-Action: a new paradigm that reframes professional software interaction as deterministic program synthesisrather than sequential visual control. To validate this paradigm in the most demanding environments, weintroduce ComCADBench, the first benchmark for agents operating real industrial CAD software. Ourexperiments reveal a substantial paradigm gap: frontier proprietary models achieve near-zero successunder GUI-based interaction, whereas COM-based execution yields substantial immediate gains. Tobridge the remaining gap between syntactic correctness and geometric accuracy, we develop ComActor, aself-correcting agent trained through a progressive three-stage framework, alongside ComForge, a scalableplatform for large-scale training in Windows containers. Extensive experiments show that C

Understanding how online narratives travel through coalitions is critical for identifying information disorder, yet computational analyses often rely on conservative network constructions that erase initially sparse but salient signals. This paper proposes a novel multi-layer framework that captures low-frequency signals of emerging information disorder allowing for locating where online discourse is reframed and amplified over time. The use case is 14 years of Italian discourse on X regarding the Human Papillomavirus (HPV) vaccine across three pivotal epochs (2010-2024). Utilizing hashtag co-occurrence networks, we introduce a dual-layer approach. We first identify robust core discourse coalitions through conservative community detection, revealing a stable prevention-oriented backbone contrasted with increasingly separable skepticism coalitions. We then introduce a coverage layer and project fringe hashtags into core coalitions based on weighted connectivity. Using a manually labelled set of skeptical and conspiratorial seed tweets, we demonstrate that this core-coverage projection significantly improves the recovery of long-tail, problematic hashtags while preserving an interpre

Organizations have widely deployed generative AI tools, yet productivity gains remain uneven, suggesting that how people use AI matters as much as whether they have access. We conducted a field experiment with 388 employees at a Fortune 500 retailer to test two scaffolding interventions for human-AI collaboration. All participants had access to the same AI tool; we varied only the structure surrounding its use. A behavioral scaffolding intervention (a structured protocol requiring joint AI use within pairs) was associated with lower document quality relative to unstructured use and substantially lower document production. A cognitive scaffolding intervention (partnership training that reframed AI as a thought partner) was associated with higher individual document quality at the top of the distribution. Treatment participants also showed greater positive belief change across the session, though sensitivity analyses suggest this likely reflects recovery from carry-over effects rather than genuine training-induced shifts. Both findings are subject to design limitations including an AM/PM session confound, differential attrition, and LLM grading sensitivity to document length.

Safety evaluations of multi-agent LLM systems often compare a direct prompt with a planner-executor pipeline and report the difference as a single "pipeline effect." We argue that this aggregate is difficult to interpret because it conflates three mechanisms: harmful intent may be reframed as plausible operational work, the planner may refuse or transform the request, and the executor may act under delegation prompts implying prior approval. To separate these factors, we introduce a five-condition controlled contrast design, evaluated on 30 synthetic harmful scenarios and an exploratory external validation set from four agent-safety benchmarks using LLM-judged compliance. Our results show that aggregate pipeline safety is not a stable architectural property. Operational reframing is the most portable risk signal, increasing compliance for GPT, Gemini, and DeepSeek across both scenario sets, while Claude is comparatively resistant. Planner behavior can offset this risk mainly through refusal; however, when the planner produces executable steps, the executor may become more compliant than under the direct operational baseline. Approval-framed delegation is sensitive to prompt design,

Information geometry has traditionally been formulated within the framework of Riemannian geometry and dual affine connections. This work aims to reframe the foundational structure of information geometry by introducing the geometric machinery of symmetric teleparallel gravity. By requiring both curvature and torsion to vanish globally on the statistical manifold, it is demonstrated that the fundamental properties of the information space can be entirely encoded in the non-metricity tensor. This approach clarifies the distinction between the general $ξ$-parameterized space and the $θ$- (or $η$-) parameterized space, mirroring the relationship among conventional general relativity, symmetric teleparallel gravity and the coincident gauge in symmetric teleparallel gravity. Specifically, the $θ$- or $η$-coordinates emerge as the special coordinates in the coincident gauge, where the connection coefficients vanish.

Recent progress in large language model (LLM) agents has largely focused on embedding self-improvement mechanisms inside the agent or searching over many concurrent variants. While these approaches can raise aggregate scores, they often yield unstable and hard-to-audit improvement trajectories, making it difficult to guarantee non-regression or to reason about failures across versions. We reframe agent improvement as \textbf{release engineering}: agents are treated as shippable artifacts, and improvement is externalized into a regression-aware release pipeline. We introduce \textbf{AgentDevel}, a release engineering pipeline that iteratively runs the current agent, produces implementation-blind, symptom-level quality signals from execution traces, synthesizes a single release candidate (RC) via executable diagnosis, and promotes it under flip-centered gating. AgentDevel features three core designs: (i) an implementation-blind LLM critic that characterizes failure appearances without accessing agent internals, (ii) script-based executable diagnosis that aggregates dominant symptom patterns and produces auditable engineering specifications, and (iii) flip-centered gating that priorit

Symplectic and complex toric quasifolds are a generalization of toric manifolds and orbifolds to the nonrational case. In this paper, we reframe these notions from the viewpoint of algebraic geometry.

Research on human-AI interaction has long framed verification of system outputs as a trust-contingent behavior that better-calibrated trust should reduce. We test this assumption in everyday human-chatbot interaction through a mixed-methods survey of 153 frequent chatbot users. Contrary to the canonical prediction, we find no detectable association between trust and verification, with the result robust across sensitivity analyses. Three further user-side practices - refinement, correction, and approval before automated actions - are widely endorsed and positively associated with satisfaction. The data reveal a substantive distinction between evaluative oversight (trust-decoupled, weakly tied to satisfaction) and interventionist oversight (weakly trust-correlated, strongly tied to satisfaction). A medium-to-large satisfaction-control gap shows that effective task outcomes do not produce a felt sense of agency. Qualitative findings identify instrumental mental models, failure-mode-specific doubt, and demand for epistemic infrastructure. We reframe user-side oversight as routine epistemic governance compatible with trust, and derive four design directions for scaffolded oversight in c

A proven therapeutic technique to overcome negative thoughts is to replace them with a more hopeful "reframed thought." Although therapy can help people practice and learn this Cognitive Reframing of Negative Thoughts, clinician shortages and mental health stigma commonly limit people's access to therapy. In this paper, we conduct a human-centered study of how language models may assist people in reframing negative thoughts. Based on psychology literature, we define a framework of seven linguistic attributes that can be used to reframe a thought. We develop automated metrics to measure these attributes and validate them with expert judgements from mental health practitioners. We collect a dataset of 600 situations, thoughts and reframes from practitioners and use it to train a retrieval-enhanced in-context learning model that effectively generates reframed thoughts and controls their linguistic attributes. To investigate what constitutes a "high-quality" reframe, we conduct an IRB-approved randomized field study on a large mental health website with over 2,000 participants. Amongst other findings, we show that people prefer highly empathic or specific reframes, as opposed to refram

Large Language Models (LLMs) are widely deployed in diverse real-world settings, yet remain vulnerable to jailbreaking, where prompt-based attacks bypass safety filters. We present THREAT (Targeted Harmful generation via Reframing and Exploitation of Adversarial Tactics), a reasoning-driven framework that coordinates multiple LLMs in an iterative search loop to find textual jailbreak prompts. We formulate prompt discovery as a nonconvex optimization problem and provide an efficient solution that lowers runtime and improves attack effectiveness. Across diverse datasets and model architectures, THREAT delivers higher attack success rates with lower computational cost than prior methods. The crafted prompts were flagged as harmful in fewer than 1% of cases, compared with about 50% refusals for the corresponding unmodified prompts. These findings reveal previously undetected vulnerabilities in aligned LLMs and position THREAT as a practical tool for proactively strengthening the safety of foundation models.