23 citations · 49 across the 16 of their papers we have counts for
17 papers
Frustratingly Simple Black-Box Adaptation of Language Models via Logit Bias
Ofek I. Cohen, Lior Shani, Aviv Rosenberg +3
Many organizations aim to adapt language models for internal use, both to improve performance on domain-specific tasks and to address privacy concerns around sensitive data. Howeve…
Latent Reasoning with Supervised Thinking States
Ido Amos, Avi Caciularu, Mor Geva +4
Reasoning with a chain-of-thought (CoT) enables Large Language Models (LLMs) to solve complex tasks but incurs significant inference costs due to the generation of long rationales.…
Reinforcement Learning with Discrete Diffusion Policies for Combinatorial Action Spaces
Haitong Ma, Ofir Nabati, Aviv Rosenberg +7
Reinforcement learning (RL) struggles to scale to large, combinatorial action spaces common in many real-world problems. This paper introduces a novel framework for training discre…
Enhancing Personalized Multi-Turn Dialogue with Curiosity Reward
Yanming Wan, Jiaxing Wu, Marwa Abdulhai +2
Effective conversational agents like large language models (LLMs) must personalize their interactions to adapt to user preferences, personalities, and attributes across diverse dom…
Embedding-Aligned Language Models
Guy Tennenholtz, Yinlam Chow, Chih-Wei Hsu +3
We propose a novel approach for training large language models (LLMs) to adhere to objectives defined within a latent embedding space. Our method leverages reinforcement learning (…
Offline Regularised Reinforcement Learning for Large Language Models Alignment
Pierre Harvey Richemond, Yunhao Tang, Daniel Guo +15
The dominant framework for alignment of large language models (LLM), whether through reinforcement learning from human feedback or direct preference optimisation, is to learn from…
Multi-turn Reinforcement Learning from Preference Human Feedback
Lior Shani, Aviv Rosenberg, Asaf Cassel +10
Reinforcement Learning from Human Feedback (RLHF) has become the standard approach for aligning Large Language Models (LLMs) with human preferences, allowing LLMs to demonstrate re…
Demystifying Embedding Spaces using Large Language Models
Guy Tennenholtz, Yinlam Chow, Chih-Wei Hsu +6
Embeddings have become a pivotal means to represent complex, multi-faceted information about entities, concepts, and relationships in a condensed and useful format. Nevertheless, t…
Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedback
Paul Roit, Johan Ferret, Lior Shani +16
Despite the seeming success of contemporary grounded text generation systems, they often tend to generate factually inconsistent text with respect to their input. This phenomenon i…
Reinforcement Learning with History-Dependent Dynamic Contexts
Guy Tennenholtz, Nadav Merlis, Lior Shani +2
We introduce Dynamic Contextual Markov Decision Processes (DCMDPs), a novel reinforcement learning framework for history-dependent environments that generalizes the contextual MDP…
Reinforcement Learning with a Terminator
Guy Tennenholtz, Nadav Merlis, Lior Shani +5
We present the problem of reinforcement learning with exogenous termination. We define the Termination Markov Decision Process (TerMDP), an extension of the MDP framework, in which…
Online Apprenticeship Learning
Lior Shani, Tom Zahavy, Shie Mannor
In Apprenticeship Learning (AL), we are given a Markov Decision Process (MDP) without access to the cost function. Instead, we observe trajectories sampled by an expert that acts a…
Mirror Descent Policy Optimization
Manan Tomar, Lior Shani, Yonathan Efroni +1
Mirror descent (MD), a well-known first-order method in constrained convex optimization, has recently been shown as an important tool to analyze trust-region algorithms in reinforc…
Optimistic Policy Optimization with Bandit Feedback
Yonathan Efroni, Lior Shani, Aviv Rosenberg +1
Policy optimization methods are one of the most widely used classes of Reinforcement Learning (RL) algorithms. Yet, so far, such methods have been mostly analyzed from an optimizat…
Adaptive Trust Region Policy Optimization: Global Convergence and Faster Rates for Regularized MDPs
Lior Shani, Yonathan Efroni, Shie Mannor
Trust region policy optimization (TRPO) is a popular and empirically successful policy search algorithm in Reinforcement Learning (RL) in which a surrogate problem, that restricts…
Multi Instance Learning For Unbalanced Data
Mark Kozdoba, Edward Moroshko, Lior Shani +4
In the context of Multi Instance Learning, we analyze the Single Instance (SI) learning objective. We show that when the data is unbalanced and the family of classifiers is suffici…
Exploration Conscious Reinforcement Learning Revisited
Lior Shani, Yonathan Efroni, Shie Mannor
The Exploration-Exploitation tradeoff arises in Reinforcement Learning when one cannot tell if a policy is optimal. Then, there is a constant need to explore new actions instead of…