3 citations · 11 across the 14 of their papers we have counts for
16 papers
Characterizing Web Search by Conversational LLM Agents: From Search Decisions and Strategies to Results and Responses
Mahsa Amani, Seungeon Lee, Abhisek Dash +9
Conversational LLM agents increasingly rely on Web search, yet the end-to-end lifecycle of agentic search remains poorly understood. We present the first study of Web search across…
Temporal Context Reinstatement Drives Episodic-Like Order Memory in Long-Context Language Models
Mathis Pink, Vy Ai Vo, Qinyuan Wu +7
Human episodic memory supports the retrieval of experiences that unfold over extended timescales, yet the computational mechanisms underlying this ability remain debated due to the…
Fine-tuning vs. In-context Learning in Large Language Models: A Formal Language Learning Perspective
Bishwamittra Ghosh, Soumi Das, Till Speicher +5
Large language models (LLMs) operate in two fundamental learning modes - fine-tuning (FT) and in-context learning (ICL) - raising key questions about which mode yields greater lang…
To Call or Not to Call: A Framework to Assess and Optimize LLM Tool Calling
Qinyuan Wu, Soumi Das, Mahsa Amani +5
Agentic AI architectures augment LLMs with external tools, unlocking strong capabilities but potentially incurring substantial costs. Moreover, tool use is not always beneficial: r…
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…
Characterizing Web Search in The Age of Generative AI
Elisabeth Kirsten, Jost Grosse Perdekamp, Qinyuan Wu +3
The advent of LLMs has given rise to generative search, a new search paradigm in which LLMs retrieve information from the web related to a query and synthesize it into a single, co…
Understanding the Interplay between Memorization and Learning in Large Language Models
Bishwamittra Ghosh, Soumi Das, Qinyuan Wu +4
We investigate foundational questions about the interplay between memorization and learning in large language models (LLMs). When an LLM generates a string, can we disentangle the…
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…
Position: Episodic Memory is the Missing Piece for Long-Term LLM Agents
Mathis Pink, Qinyuan Wu, Vy Ai Vo +4
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 learni…
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).…
Assessing Episodic Memory in LLMs with Sequence Order Recall Tasks
Mathis Pink, Vy A. Vo, Qinyuan Wu +7
Current LLM benchmarks focus on evaluating models' memory of facts and semantic relations, primarily assessing semantic aspects of long-term memory. However, in humans, long-term m…
Understanding Memorisation in LLMs: Dynamics, Influencing Factors, and Implications
Till Speicher, Mohammad Aflah Khan, Qinyuan Wu +5
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…
Towards Reliable Latent Knowledge Estimation in LLMs: Zero-Prompt Many-Shot Based Factual Knowledge Extraction
Qinyuan Wu, Mohammad Aflah Khan, Soumi Das +7
In this paper, we focus on the challenging task of reliably estimating factual knowledge that is embedded inside large language models (LLMs). To avoid reliability concerns with pr…
A Negation Quantum Decision Model to Predict the Interference Effect in Categorization
Qinyuan Wu, Yong Deng
Categorization is a significant task in decision-making, which is a key part of human behavior. An interference effect is caused by categorization in some cases, which breaks the t…
Exponential Negation of a Probability Distribution
Qinyuan Wu, Yong Deng, Neal Xiong
Negation operation is important in intelligent information processing. Different with existing arithmetic negation, an exponential negation is presented in this paper. The new nega…