Search Results for author:
Found 7 papers, 1 papers with code
Revisiting Privacy, Utility, and Efficiency Trade-offs when Fine-Tuning Large Language Models
A number of recent works in privacy research have attempted to mitigate privacy risks posed by memorizing fine-tuning data by using differentially private training methods (e. g., DP), albeit at a significantly higher computational cost (inefficiency).
Position: Episodic Memory is the Missing Piece for Long-Term LLM Agents
As Large Language Models (LLMs) evolve from text-completion tools into fully fledged agents operating in dynamic environments, they must address the challenge of continually learning and retaining long-term knowledge.
Assessing Episodic Memory in LLMs with Sequence Order Recall Tasks
To address the gap in evaluating memory in LLMs, we introduce Sequence Order Recall Tasks (SORT), which we adapt from tasks used to study episodic memory in cognitive psychology.
Understanding Memorisation in LLMs: Dynamics, Influencing Factors, and Implications
Understanding whether and to what extent large language models (LLMs) have memorised training data has important implications for the reliability of their output and the privacy of their training data.
Towards Reliable Latent Knowledge Estimation in LLMs: Zero-Prompt Many-Shot Based Factual Knowledge Extraction
Our knowledge estimator is both conceptually simpler (i. e., doesn't depend on meta-linguistic judgments of LLMs) and easier to apply (i. e., is not LLM-specific), and we demonstrate that it can surface more of the latent knowledge embedded in LLMs.
A Negation Quantum Decision Model to Predict the Interference Effect in Categorization
Categorization is a significant task in decision-making, which is a key part of human behavior.
Exponential Negation of a Probability Distribution
Some basic properties of the proposed negation is investigated, we find that the fix point is the uniform probability distribution.
