LLM multi-agent systems on lattices show bias-driven order-disorder crossovers instead of true phase transitions, with extracted effective couplings and fields serving as model-specific fingerprints.
The bias is in the details: An assessment of cognitive bias in llms
5 Pith papers cite this work. Polarity classification is still indexing.
citation-role summary
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
LLMs for code vulnerability detection show average susceptibility of 33.2% to framing, 23.5% to anchoring, and 18.4% to halo effects, with a black-box attack suppressing up to 97% of detections.
Primacy, anchoring, and order-dependence are architecturally necessary in autoregressive models due to causal masking constraints, with supporting evidence from theorems, LLM fits, and human experiments.
LLMs encode accurate but brittle internal beliefs about latent game states and convert them poorly into actions, creating systematic gaps that explain strategic failures.
A CVaR-aware agentic framework for 6G network slicing eliminates URLLC SLA violations by shifting LLM decisions from mean latency to tail-risk distributions predicted by digital twins.
citing papers explorer
-
Collective Alignment in LLM Multi-Agent Systems: Disentangling Bias from Cooperation via Statistical Physics
LLM multi-agent systems on lattices show bias-driven order-disorder crossovers instead of true phase transitions, with extracted effective couplings and fields serving as model-specific fingerprints.
-
Words Speak Louder Than Code: Investigating Cognitive Heuristics in LLM-Based Code Vulnerability Detection
LLMs for code vulnerability detection show average susceptibility of 33.2% to framing, 23.5% to anchoring, and 18.4% to halo effects, with a black-box attack suppressing up to 97% of detections.
-
Bias by Necessity: Impossibility Theorems for Sequential Processing with Convergent AI and Human Validation
Primacy, anchoring, and order-dependence are architecturally necessary in autoregressive models due to causal masking constraints, with supporting evidence from theorems, LLM fits, and human experiments.
-
Why Do LLMs Struggle in Strategic Play? Broken Links Between Observations, Beliefs, and Actions
LLMs encode accurate but brittle internal beliefs about latent game states and convert them poorly into actions, creating systematic gaps that explain strategic failures.
-
LLM-Based Agentic Negotiation for 6G: Addressing Uncertainty Neglect and Tail-Event Risk
A CVaR-aware agentic framework for 6G network slicing eliminates URLLC SLA violations by shifting LLM decisions from mean latency to tail-risk distributions predicted by digital twins.