5 papers
Textual Planning with Explicit Latent Transitions
Eliezer Shlomi, Ido Levy, Eilam Shapira +6
Planning with LLMs is bottlenecked by token-by-token generation and repeated full forward passes, making multi-step lookahead and rollout-based search expensive in latency and comp…
LIBERTy: A Causal Framework for Benchmarking Concept-Based Explanations of LLMs with Structural Counterfactuals
Gilat Toker, Nitay Calderon, Ohad Amosy +1
Concept-based explanations quantify how high-level concepts (e.g., gender or experience) influence model behavior, which is crucial for decision-makers in high-stakes domains. Rece…
Donors and Recipients: On Asymmetric Transfer Across Tasks and Languages with Parameter-Efficient Fine-Tuning
Kajetan Dymkiewicz, Ivan Vulic, Helen Yannakoudakis +3
Large language models (LLMs) perform strongly across tasks and languages, yet how improvements in one task or language affect other tasks and languages remains poorly understood. W…
TabSTAR: A Tabular Foundation Model for Tabular Data with Text Fields
Alan Arazi, Eilam Shapira, Roi Reichart
While deep learning has achieved remarkable success across many domains, it has historically underperformed on tabular learning tasks, which remain dominated by gradient boosting d…
AdaptiVocab: Enhancing LLM Efficiency in Focused Domains through Lightweight Vocabulary Adaptation
Itay Nakash, Nitay Calderon, Eyal Ben David +2
Large Language Models (LLMs) have shown impressive versatility as general purpose models. However, their broad applicability comes at a high-cost computational overhead, particular…