20 results for “Contextual Stability”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
The paper introduces a new protocol, GT-MCP, to secure large language models against prompt-injection and context-poisoning attacks.
Ziqing Man, Di Wu, Jia-Chen Gu, Junyi Zhang +2 more
The authors introduce KEEP-Bench, a diagnostic benchmark to assess compression faithfulness and evaluate the performance of context compression models.
Wei Yang, Bryce Kan, Shixuan Li, Li Li +4 more
The paper proposes a framework called RaMem to improve the validity of retrieved memories in long-term memory systems for LLM agents.
This paper proposes the stable signal principle to explain the convergence behavior of retraining in performative prediction systems, revealing regularization as a natural force to control performativ…
This paper introduces a task-oriented randomization methodology to stabilize black-box models while leveraging prior information.
The paper argues that prompt injection is a fundamental vulnerability in AI agents, proposing that Contextual Integrity (CI) offers a principled framework to understand and mitigate context-sensitive…
The paper proposes a novel information-geometric framework to analyze LLM stability by integrating task utility, external entropy, and internal structural proxies, showing this composite score improve…
This paper proposes a method to mitigate hallucinations in multi-agent LLM systems by synchronizing shared knowledge states between agents.
This paper characterizes stabilizability of stochastic dynamic matching on hypergraphs using the arrival rates and incidence matrix, and proposes a stabilizing policy.
The paper addresses the vulnerability of zero-knowledge proximity proofs in stateful systems by proposing Zairn-ZKP, a method that embeds operational context (like drop identity and policy version) di…
This paper introduces online assignment policies for stochastic matching on hypergraphs, which are maximally stable and allow for the derivation of necessary and sufficient stability criteria.
The paper introduces Context-Dependent Argumentation Frameworks (CDAFs) to model how an agent strategically manipulates the success of arguments by choosing the external evaluation context.
The paper introduces a generalized, operator-based mathematical framework to explicitly model and quantify structural discrepancies (conflicts) between raw and contextual data, treating conflict as an…
The paper introduces 'brittle safety,' a failure mode where aligned language models fail to adapt their safety behavior when a situational context changes, and proposes state-aware validation to detec…
Lu Yi, Runlin Lei, Liuyi Yao, Yuexiang Xie +5 more
The paper introduces Adaptive Context Management (AdaCoM), an external context manager that uses reinforcement learning to improve the performance of frozen LLM agents on long-horizon tasks by intelli…
Wenjie Fu, Xiaoting Qin, Jue Zhang, Qingwei Lin +4 more
The paper introduces CI-Work, a benchmark demonstrating that current enterprise LLM agents frequently leak sensitive information while performing tasks, suggesting that privacy protection requires arc…
The paper extends a statistics-first linear-algebraic framework for contextuality in prepare-measure scenarios to operational scenarios with sequential transformations, providing a decision procedure…
Wajeeha Tahir, Anna Tegon, Lionnus Kesting, Gamze İslamoğlu +3 more
This paper introduces Spatial-TRM, a compact recursive model that improves spatial context prediction in natural images.