6 papers
The Algorithmic Self-Portrait: Deconstructing Memory in ChatGPT
Abhisek Dash, Soumi Das, Elisabeth Kirsten +6
To enable personalized and context-aware interactions, conversational AI systems have introduced a new mechanism: Memory. Memory creates what we refer to as the Algorithmic Self-po…
In Agents We Trust, but Who Do Agents Trust? Latent Source Preferences Steer LLM Generations
Mohammad Aflah Khan, Mahsa Amani, Soumi Das +5
Agents based on Large Language Models (LLMs) are increasingly being deployed as interfaces to information on online platforms. These agents filter, prioritize, and synthesize infor…
LoRA on the Go: Instance-level Dynamic LoRA Selection and Merging
Seungeon Lee, Soumi Das, Manish Gupta +1
Low-Rank Adaptation (LoRA) has emerged as a parameter-efficient approach for fine-tuning large language models. However, conventional LoRA adapters are typically trained for a sing…
Rethinking Memorization Measures and their Implications in Large Language Models
Bishwamittra Ghosh, Soumi Das, Qinyuan Wu +4
Concerned with privacy threats, memorization in LLMs is often seen as undesirable, specifically for learning. In this paper, we study whether memorization can be avoided when optim…
Rote Learning Considered Useful: Generalizing over Memorized Data in LLMs
Qinyuan Wu, Soumi Das, Mahsa Amani +4
Rote learning is a memorization technique based on repetition. Many researchers argue that rote learning hinders generalization because it encourages verbatim memorization rather t…
Revisiting Privacy, Utility, and Efficiency Trade-offs when Fine-Tuning Large Language Models
Soumi Das, Camila Kolling, Mohammad Aflah Khan +5
We study the inherent trade-offs in minimizing privacy risks and maximizing utility, while maintaining high computational efficiency, when fine-tuning large language models (LLMs).…