39 citations · 121 across the 19 of their papers we have counts for
21 papers
Olmo 3
Team Olmo, :, Allyson Ettinger +66
We introduce Olmo 3, a family of state-of-the-art, fully-open language models at the 7B and 32B parameter scales. Olmo 3 model construction targets long-context reasoning, function…
DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research
Rulin Shao, Akari Asai, Shannon Zejiang Shen +18
Deep research agents perform multi-step research to produce long-form, well-attributed answers. However, most open deep research agents are trained on easily verifiable short-form…
RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments
Zhiyuan Zeng, Hamish Ivison, Yiping Wang +14
We introduce Reinforcement Learning (RL) with Adaptive Verifiable Environments (RLVE), an approach using verifiable environments that procedurally generate problems and provide alg…
A Good Plan is Hard to Find: Aligning Models with Preferences is Misaligned with What Helps Users
Nishant Balepur, Matthew Shu, Yoo Yeon Sung +5
To assist users in complex tasks, LLMs generate plans: step-by-step instructions towards a goal. While alignment methods aim to ensure LLM plans are helpful, they train (RLHF) or e…
The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality
Benjamin Newman, Abhilasha Ravichander, Jaehun Jung +5
Language models are prone to hallucination - generating text that is factually incorrect. Finetuning models on high-quality factual information can potentially reduce hallucination…
The Delta Learning Hypothesis: Preference Tuning on Weak Data can Yield Strong Gains
Scott Geng, Hamish Ivison, Chun-Liang Li +4
Improvements in language models are often driven by improving the quality of the data we train them on, which can be limiting when strong supervision is scarce. In this work, we sh…
Generalizing Verifiable Instruction Following
Valentina Pyatkin, Saumya Malik, Victoria Graf +5
A crucial factor for successful human and AI interaction is the ability of language models or chatbots to follow human instructions precisely. A common feature of instructions are…
Large-Scale Data Selection for Instruction Tuning
Hamish Ivison, Muru Zhang, Faeze Brahman +2
Selecting high-quality training data from a larger pool is a crucial step when instruction-tuning language models, as carefully curated datasets often produce models that outperfor…
TESS 2: A Large-Scale Generalist Diffusion Language Model
Jaesung Tae, Hamish Ivison, Sachin Kumar +1
We introduce TESS 2, a general instruction-following diffusion language model that outperforms contemporary instruction-tuned diffusion models, as well as matches and sometimes exc…
2 OLMo 2 Furious
Team OLMo, Pete Walsh, Luca Soldaini +40
We present OLMo 2, the next generation of our fully open language models. OLMo 2 includes a family of dense autoregressive language models at 7B, 13B and 32B scales with fully rele…
Tulu 3: Pushing Frontiers in Open Language Model Post-Training
Nathan Lambert, Jacob Morrison, Valentina Pyatkin +20
Language model post-training is applied to refine behaviors and unlock new skills across a wide range of recent language models, but open recipes for applying these techniques lag…
Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning
Sriyash Poddar, Yanming Wan, Hamish Ivison +2
Reinforcement Learning from Human Feedback (RLHF) is a powerful paradigm for aligning foundation models to human values and preferences. However, current RLHF techniques cannot acc…
Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback
Hamish Ivison, Yizhong Wang, Jiacheng Liu +6
Learning from preference feedback has emerged as an essential step for improving the generation quality and performance of modern language models (LMs). Despite its widespread use,…
OLMo: Accelerating the Science of Language Models
Dirk Groeneveld, Iz Beltagy, Pete Walsh +40
Language models (LMs) have become ubiquitous in both NLP research and in commercial product offerings. As their commercial importance has surged, the most powerful models have beco…
Camels in a Changing Climate: Enhancing LM Adaptation with Tulu 2
Hamish Ivison, Yizhong Wang, Valentina Pyatkin +8
Since the release of TÜLU [Wang et al., 2023b], open resources for instruction tuning have developed quickly, from better base models to new finetuning techniques. We test and inco…
How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources
Yizhong Wang, Hamish Ivison, Pradeep Dasigi +8
In this work we explore recent advances in instruction-tuning language models on a range of open instruction-following datasets. Despite recent claims that open models can be on pa…
TESS: Text-to-Text Self-Conditioned Simplex Diffusion
Rabeeh Karimi Mahabadi, Hamish Ivison, Jaesung Tae +4
Diffusion models have emerged as a powerful paradigm for generation, obtaining strong performance in various continuous domains. However, applying continuous diffusion models to na…
HINT: Hypernetwork Instruction Tuning for Efficient Zero- & Few-Shot Generalisation
Hamish Ivison, Akshita Bhagia, Yizhong Wang +2
Recent NLP models have shown the remarkable ability to effectively generalise `zero-shot' to new tasks using only natural language instructions as guidance. However, many of these…
Data-Efficient Finetuning Using Cross-Task Nearest Neighbors
Hamish Ivison, Noah A. Smith, Hannaneh Hajishirzi +1
Obtaining labeled data to train a model for a task of interest is often expensive. Prior work shows training models on multitask data augmented with task descriptions (prompts) eff…
Hyperdecoders: Instance-specific decoders for multi-task NLP
Hamish Ivison, Matthew E. Peters
We investigate input-conditioned hypernetworks for multi-tasking in NLP, generating parameter-efficient adaptations for a decoder using a hypernetwork conditioned on the output of…
Local Interpretations for Explainable Natural Language Processing: A Survey
Siwen Luo, Hamish Ivison, Caren Han +1
As the use of deep learning techniques has grown across various fields over the past decade, complaints about the opaqueness of the black-box models have increased, resulting in an…