10 citations · 56 across the 36 of their papers we have counts for
37 papers
Cold-Start Personalization via Training-Free Priors from Structured World Models
Avinandan Bose, Shuyue Stella Li, Faeze Brahman +6
Cold-start personalization requires inferring user preferences through interaction when no user-specific historical data is available. The core challenge is a routing problem: each…
Small Reward Models via Backward Inference
Yike Wang, Faeze Brahman, Shangbin Feng +3
Reward models (RMs) play a central role throughout the language model (LM) pipeline, particularly in non-verifiable domains. However, the dominant LLM-as-a-Judge paradigm relies on…
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…
Reasoning Up the Instruction Ladder for Controllable Language Models
Zishuo Zheng, Vidhisha Balachandran, Chan Young Park +2
As large language model (LLM) based systems take on high-stakes roles in real-world decision-making, they must reconcile competing instructions from multiple sources within a singl…
Train for Truth, Keep the Skills: Binary Retrieval-Augmented Reward Mitigates Hallucinations
Tong Chen, Akari Asai, Luke Zettlemoyer +2
Language models often generate factually incorrect information unsupported by their training data, a phenomenon known as extrinsic hallucination. Existing mitigation approaches oft…
PrefDisco: Benchmarking Proactive Personalized Reasoning
Shuyue Stella Li, Avinandan Bose, Faeze Brahman +4
Current large language model (LLM) development treats task-solving and preference-alignment as separate challenges, optimizing first for objective correctness, then for alignment t…
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…
Let Them Down Easy! Contextual Effects of LLM Guardrails on User Perceptions and Preferences
Mingqian Zheng, Wenjia Hu, Patrick Zhao +5
Current LLMs are trained to refuse potentially harmful input queries regardless of whether users actually had harmful intents, causing a tradeoff between safety and user experience…
ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data
Tong Chen, Faeze Brahman, Jiacheng Liu +5
Language models (LMs) can memorize and reproduce segments from their pretraining data verbatim even in non-adversarial settings, raising concerns about copyright, plagiarism, priva…
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…
ALFA: Aligning LLMs to Ask Good Questions A Case Study in Clinical Reasoning
Shuyue Stella Li, Jimin Mun, Faeze Brahman +7
Large language models (LLMs) often fail to ask effective questions under uncertainty, making them unreliable in domains where proactive information-gathering is essential for decis…
IssueBench: Millions of Realistic Prompts for Measuring Issue Bias in LLM Writing Assistance
Paul Röttger, Musashi Hinck, Valentin Hofmann +4
Large language models (LLMs) are helping millions of users write texts about diverse issues, and in doing so expose users to different ideas and perspectives. This creates concerns…
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…
Multi-Attribute Constraint Satisfaction via Language Model Rewriting
Ashutosh Baheti, Debanjana Chakraborty, Faeze Brahman +6
Obeying precise constraints on top of multiple external attributes is a common computational problem underlying seemingly different domains, from controlled text generation to prot…
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…
RESTOR: Knowledge Recovery in Machine Unlearning
Keivan Rezaei, Khyathi Chandu, Soheil Feizi +3
Large language models trained on web-scale corpora can memorize undesirable data containing misinformation, copyrighted material, or private or sensitive information. Recently, sev…
Hybrid Preferences: Learning to Route Instances for Human vs. AI Feedback
Lester James V. Miranda, Yizhong Wang, Yanai Elazar +6
Learning from human feedback has enabled the alignment of language models (LMs) with human preferences. However, collecting human preferences is expensive and time-consuming, with…
HAICOSYSTEM: An Ecosystem for Sandboxing Safety Risks in Human-AI Interactions
Xuhui Zhou, Hyunwoo Kim, Faeze Brahman +9
AI agents are increasingly autonomous in their interactions with human users and tools, leading to increased interactional safety risks. We present HAICOSYSTEM, a framework examini…
AI-LieDar: Examine the Trade-off Between Utility and Truthfulness in LLM Agents
Zhe Su, Xuhui Zhou, Sanketh Rangreji +4
Truthfulness (adherence to factual accuracy) and utility (satisfying human needs and instructions) are both fundamental aspects of Large Language Models, yet these goals often conf…
Trust or Escalate: LLM Judges with Provable Guarantees for Human Agreement
Jaehun Jung, Faeze Brahman, Yejin Choi
We present a principled approach to provide LLM-based evaluation with a rigorous guarantee of human agreement. We first propose that a reliable evaluation method should not uncriti…
The Art of Saying No: Contextual Noncompliance in Language Models
Faeze Brahman, Sachin Kumar, Vidhisha Balachandran +11
Chat-based language models are designed to be helpful, yet they should not comply with every user request. While most existing work primarily focuses on refusal of "unsafe" queries…
How to Train Your Fact Verifier: Knowledge Transfer with Multimodal Open Models
Jaeyoung Lee, Ximing Lu, Jack Hessel +5
Given the growing influx of misinformation across news and social media, there is a critical need for systems that can provide effective real-time verification of news claims. Larg…
WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models
Liwei Jiang, Kavel Rao, Seungju Han +8
We introduce WildTeaming, an automatic LLM safety red-teaming framework that mines in-the-wild user-chatbot interactions to discover 5.7K unique clusters of novel jailbreak tactics…