Creates LoCoMo benchmark dataset for very long-term LLM conversational memory and shows current models struggle with lengthy dialogues and long-range temporal dynamics.
Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers) , pages=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2verdicts
UNVERDICTED 2representative citing papers
Authors develop a multi-dimensional neuron screening framework and adaptive masking method to causally validate and steer emotion and rhetoric neurons in LLMs, with experiments on five datasets.
citing papers explorer
-
Evaluating Very Long-Term Conversational Memory of LLM Agents
Creates LoCoMo benchmark dataset for very long-term LLM conversational memory and shows current models struggle with lengthy dialogues and long-range temporal dynamics.
-
Are Emotion and Rhetoric Neurons in LLM? Neuron Recognition and Adaptive Masking for Emotion-Rhetoric Prediction Steering
Authors develop a multi-dimensional neuron screening framework and adaptive masking method to causally validate and steer emotion and rhetoric neurons in LLMs, with experiments on five datasets.