OptiVerse is a new benchmark spanning neglected optimization domains that shows LLMs suffer sharp accuracy drops on hard problems due to modeling and logic errors, with a Dual-View Auditor Agent proposed to improve performance.
Title resolution pending
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
years
2026 7verdicts
UNVERDICTED 7representative citing papers
Large-scale statistical analysis of four harmful language datasets reveals that interactions between annotator characteristics and linguistic cues drive annotation variation, with lexical features and attitudes prominent but patterns varying by dataset.
Embedding-based defenses fail against attacks that align malicious message embeddings with benign ones in LLM multi-agent systems, but token-level confidence scores improve robustness by enabling better pruning of suspicious messages.
CAP is a reinforcement-learning-driven prompt optimization framework that suppresses target knowledge in LLMs while preserving general capabilities, enabling reversible unlearning without any parameter updates.
DCM-Agent improves LLM performance on multi-paradigm optimization problems by 11-21% via dual-cluster memory construction and dynamic inference guidance.
DMoA is a differentiable multi-agent LLM framework with recurrent context-aware routing and predictive entropy self-supervision that claims SOTA results on 9 benchmarks through elastic agent collaboration.
Cosine similarity poorly predicts performance degradation from layer removal in LLMs, making direct accuracy-drop ablation a more reliable relevance metric.
citing papers explorer
-
OptiVerse: A Comprehensive Benchmark towards Optimization Problem Solving
OptiVerse is a new benchmark spanning neglected optimization domains that shows LLMs suffer sharp accuracy drops on hard problems due to modeling and logic errors, with a Dual-View Auditor Agent proposed to improve performance.
-
Who and What? Using Linguistic Features and Annotator Characteristics to Analyze Annotation Variation
Large-scale statistical analysis of four harmful language datasets reveals that interactions between annotator characteristics and linguistic cues drive annotation variation, with lexical features and attitudes prominent but patterns varying by dataset.
-
When Embedding-Based Defenses Fail: Rethinking Safety in LLM-Based Multi-Agent Systems
Embedding-based defenses fail against attacks that align malicious message embeddings with benign ones in LLM multi-agent systems, but token-level confidence scores improve robustness by enabling better pruning of suspicious messages.
-
CAP: Controllable Alignment Prompting for Unlearning in LLMs
CAP is a reinforcement-learning-driven prompt optimization framework that suppresses target knowledge in LLMs while preserving general capabilities, enabling reversible unlearning without any parameter updates.
-
Dual-Cluster Memory Agent: Resolving Multi-Paradigm Ambiguity in Optimization Problem Solving
DCM-Agent improves LLM performance on multi-paradigm optimization problems by 11-21% via dual-cluster memory construction and dynamic inference guidance.
-
Differentiable Mixture-of-Agents Incentivizes Swarm Intelligence of Large Language Models
DMoA is a differentiable multi-agent LLM framework with recurrent context-aware routing and predictive entropy self-supervision that claims SOTA results on 9 benchmarks through elastic agent collaboration.
-
Rethinking Layer Relevance in Large Language Models Beyond Cosine Similarity
Cosine similarity poorly predicts performance degradation from layer removal in LLMs, making direct accuracy-drop ablation a more reliable relevance metric.