HumanLLM builds a cognitive-pattern benchmark from 12,000 papers and 11,359 scenarios, achieving r=0.90 human alignment and demonstrating that an 8B model trained on pattern interactions beats a 32B baseline on multi-pattern dynamics.
Yunfan Shao, Linyang Li, Junqi Dai, and Xipeng Qiu
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2representative citing papers
A survey that introduces a taxonomy for LLM-based conversational user simulation, analyzes core techniques and evaluation methods, and identifies open challenges in the field.
citing papers explorer
-
HumanLLM: Benchmarking and Improving LLM Anthropomorphism via Human Cognitive Patterns
HumanLLM builds a cognitive-pattern benchmark from 12,000 papers and 11,359 scenarios, achieving r=0.90 human alignment and demonstrating that an 8B model trained on pattern interactions beats a 32B baseline on multi-pattern dynamics.
-
A Survey on LLM-based Conversational User Simulation
A survey that introduces a taxonomy for LLM-based conversational user simulation, analyzes core techniques and evaluation methods, and identifies open challenges in the field.