3 citations · 3 across the 8 of their papers we have counts for
8 papers
AIRA_2: Overcoming Bottlenecks in AI Research Agents
Karen Hambardzumyan, Nicolas Baldwin, Edan Toledo +22
Existing research has identified three structural performance bottlenecks in AI research agents: (1) synchronous single-GPU execution constrains sample throughput, limiting the ben…
Hallucination reduction with CASAL: Contrastive Activation Steering For Amortized Learning
Wannan, Yang, Xinchi Qiu +6
Large Language Models (LLMs) exhibit impressive capabilities but often hallucinate, confidently providing incorrect answers instead of admitting ignorance. Prior work has shown tha…
AbbIE: Autoregressive Block-Based Iterative Encoder for Efficient Sequence Modeling
Preslav Aleksandrov, Meghdad Kurmanji, Fernando Garcia Redondo +7
We introduce the Autoregressive Block-Based Iterative Encoder (AbbIE), a novel recursive generalization of the encoder-only Transformer architecture, which achieves better perplexi…
SEAT: Sparse Entity-Aware Tuning for Knowledge Adaptation while Preserving Epistemic Abstention
William F. Shen, Xinchi Qiu, Nicola Cancedda +1
Adapting LLMs with new knowledge is increasingly important, but standard fine-tuning often erodes aligned epistemic abstention: the ability to acknowledge when the model does not k…
LLM Unlearning via Neural Activation Redirection
William F. Shen, Xinchi Qiu, Meghdad Kurmanji +5
The ability to selectively remove knowledge from LLMs is highly desirable. However, existing methods often struggle with balancing unlearning efficacy and retain model utility, and…
How Data Inter-connectivity Shapes LLMs Unlearning: A Structural Unlearning Perspective
Xinchi Qiu, William F. Shen, Yihong Chen +4
While unlearning knowledge from large language models (LLMs) is receiving increasing attention, one important aspect remains unexplored. Existing approaches and benchmarks assume d…
Know When To Stop: A Study of Semantic Drift in Text Generation
Ava Spataru, Eric Hambro, Elena Voita +1
In this work, we explicitly show that modern LLMs tend to generate correct facts first, then "drift away" and generate incorrect facts later: this was occasionally observed but nev…
Spectral Filters, Dark Signals, and Attention Sinks
Nicola Cancedda
Projecting intermediate representations onto the vocabulary is an increasingly popular interpretation tool for transformer-based LLMs, also known as the logit lens. We propose a qu…