238 citations · 571 across the 27 of their papers we have counts for
27 papers
CT: Counterfactual Causal Reasoning for Sentiment Shifts in Social-Media Conversation Trees
S M Rafiuddin, Atriya Sen
Sentiment in social-media threads does not only vary across posts; it shifts as users react to claims, corrections, evidence, and hostility within a branching reply tree. We study…
Gemma 4 Technical Report
Gemma Team, Sherif El Abd, Vaibhav Aggarwal +320
We introduce Gemma 4, a new generation of open-weight, natively multimodal language models in the Gemma model family. Designed to advance compute efficiency and reasoning, the Gemm…
The Bias is in the Details: An Assessment of Cognitive Bias in LLMs
R. Alexander Knipper, Charles S. Knipper, Kaiqi Zhang +3
As Large Language Models (LLMs) are increasingly embedded in real-world decision-making processes, it becomes crucial to examine the extent to which they exhibit cognitive biases.…
CoLD: Counterfactually-Guided Length Debiasing for Process Reward Models in Mathematical Reasoning
Congmin Zheng, Jiachen Zhu, Jianghao Lin +6
Process Reward Models (PRMs) play a central role in evaluating and guiding multi-step reasoning in large language models (LLMs), especially for mathematical problem solving. Howeve…
MedGemma Technical Report
Andrew Sellergren, Sahar Kazemzadeh, Tiam Jaroensri +78
Artificial intelligence (AI) has significant potential in healthcare applications, but its training and deployment faces challenges due to healthcare's diverse data, complex tasks,…
Investigating Pedagogical Teacher and Student LLM Agents: Genetic Adaptation Meets Retrieval Augmented Generation Across Learning Style
Debdeep Sanyal, Agniva Maiti, Umakanta Maharana +4
Effective teaching requires adapting instructional strategies to accommodate the diverse cognitive and behavioral profiles of students, a persistent challenge in education and teac…
Gemma 3 Technical Report
Gemma Team, Aishwarya Kamath, Johan Ferret +209
We introduce Gemma 3, a multimodal addition to the Gemma family of lightweight open models, ranging in scale from 1 to 27 billion parameters. This version introduces vision underst…
On Teacher Hacking in Language Model Distillation
Daniil Tiapkin, Daniele Calandriello, Johan Ferret +4
Post-training of language models (LMs) increasingly relies on the following two stages: (i) knowledge distillation, where the LM is trained to imitate a larger teacher LM, and (ii)…
Humanity's Last Exam
Long Phan, Alice Gatti, Ziwen Han +1168
Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achi…
Diversity-Rewarded CFG Distillation
Geoffrey Cideron, Andrea Agostinelli, Johan Ferret +5
Generative models are transforming creative domains such as music generation, with inference-time strategies like Classifier-Free Guidance (CFG) playing a crucial role. However, CF…
Gemma 2: Improving Open Language Models at a Practical Size
Gemma Team, Morgane Riviere, Shreya Pathak +195
In this work, we introduce Gemma 2, a new addition to the Gemma family of lightweight, state-of-the-art open models, ranging in scale from 2 billion to 27 billion parameters. In th…
Assessing the Zero-Shot Capabilities of LLMs for Action Evaluation in RL
Eduardo Pignatelli, Johan Ferret, Tim Rockäschel +4
The temporal credit assignment problem is a central challenge in Reinforcement Learning (RL), concerned with attributing the appropriate influence to each actions in a trajectory f…
BOND: Aligning LLMs with Best-of-N Distillation
Pier Giuseppe Sessa, Robert Dadashi, Léonard Hussenot +17
Reinforcement learning from human feedback (RLHF) is a key driver of quality and safety in state-of-the-art large language models. Yet, a surprisingly simple and strong inference-t…
Conditional Language Policy: A General Framework for Steerable Multi-Objective Finetuning
Kaiwen Wang, Rahul Kidambi, Ryan Sullivan +17
Reward-based finetuning is crucial for aligning language policies with intended behaviors (e.g., creativity and safety). A key challenge is to develop steerable language models tha…
WARP: On the Benefits of Weight Averaged Rewarded Policies
Alexandre Ramé, Johan Ferret, Nino Vieillard +7
Reinforcement learning from human feedback (RLHF) aligns large language models (LLMs) by encouraging their generations to have high rewards, using a reward model trained on human p…
Gemma: Open Models Based on Gemini Research and Technology
Gemma Team, Thomas Mesnard, Cassidy Hardin +105
This work introduces Gemma, a family of lightweight, state-of-the art open models built from the research and technology used to create Gemini models. Gemma models demonstrate stro…
RecurrentGemma: Moving Past Transformers for Efficient Open Language Models
Aleksandar Botev, Soham De, Samuel L Smith +59
We introduce RecurrentGemma, a family of open language models which uses Google's novel Griffin architecture. Griffin combines linear recurrences with local attention to achieve ex…
Direct Language Model Alignment from Online AI Feedback
Shangmin Guo, Biao Zhang, Tianlin Liu +9
Direct alignment from preferences (DAP) methods, such as DPO, have recently emerged as efficient alternatives to reinforcement learning from human feedback (RLHF), that do not requ…
WARM: On the Benefits of Weight Averaged Reward Models
Alexandre Ramé, Nino Vieillard, Léonard Hussenot +4
Aligning large language models (LLMs) with human preferences through reinforcement learning (RLHF) can lead to reward hacking, where LLMs exploit failures in the reward model (RM)…
A Survey of Temporal Credit Assignment in Deep Reinforcement Learning
Eduardo Pignatelli, Johan Ferret, Matthieu Geist +4
The Credit Assignment Problem (CAP) refers to the longstanding challenge of Reinforcement Learning (RL) agents to associate actions with their long-term consequences. Solving the C…
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…
Lazy-MDPs: Towards Interpretable Reinforcement Learning by Learning When to Act
Alexis Jacq, Johan Ferret, Olivier Pietquin +1
Traditionally, Reinforcement Learning (RL) aims at deciding how to act optimally for an artificial agent. We argue that deciding when to act is equally important. As humans, we dri…
More Efficient Exploration with Symbolic Priors on Action Sequence Equivalences
Toby Johnstone, Nathan Grinsztajn, Johan Ferret +1
Incorporating prior knowledge in reinforcement learning algorithms is mainly an open question. Even when insights about the environment dynamics are available, reinforcement learni…
There Is No Turning Back: A Self-Supervised Approach for Reversibility-Aware Reinforcement Learning
Nathan Grinsztajn, Johan Ferret, Olivier Pietquin +2
We propose to learn to distinguish reversible from irreversible actions for better informed decision-making in Reinforcement Learning (RL). From theoretical considerations, we show…