31 citations · 109 across the 36 of their papers we have counts for
38 papers
XYBench: Can LLMs Respond Pragmatically to Queries with Misconceptions?
Akhila Yerukola, Jena D. Hwang, Mingqian Zheng +5
When non-expert users ask LLMs for assistance, their queries can often have misconceptions (e.g., "How do I parse XML with regex?"). In such cases, often referred to as the XY-prob…
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…
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…
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…
Is It JUST Semantics? A Case Study of Discourse Particle Understanding in LLMs
William Sheffield, Kanishka Misra, Valentina Pyatkin +3
Discourse particles are crucial elements that subtly shape the meaning of text. These words, often polyfunctional, give rise to nuanced and often quite disparate semantic/discourse…
RewardBench 2: Advancing Reward Model Evaluation
Saumya Malik, Valentina Pyatkin, Sander Land +4
Reward models are used throughout the post-training of language models to capture nuanced signals from preference data and provide a training target for optimization across instruc…
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…
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…
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…
SafetyAnalyst: Interpretable, Transparent, and Steerable Safety Moderation for AI Behavior
Jing-Jing Li, Valentina Pyatkin, Max Kleiman-Weiner +7
The ideal AI safety moderation system would be both structurally interpretable (so its decisions can be reliably explained) and steerable (to align to safety standards and reflect…
Diverging Preferences: When do Annotators Disagree and do Models Know?
Michael JQ Zhang, Zhilin Wang, Jena D. Hwang +6
We examine diverging preferences in human-labeled preference datasets. We develop a taxonomy of disagreement sources spanning ten categories across four high-level classes and find…
Explicating the Implicit: Argument Detection Beyond Sentence Boundaries
Paul Roit, Aviv Slobodkin, Eran Hirsch +4
Detecting semantic arguments of a predicate word has been conventionally modeled as a sentence-level task. The typical reader, however, perfectly interprets predicate-argument rela…
Self-Directed Synthetic Dialogues and Revisions Technical Report
Nathan Lambert, Hailey Schoelkopf, Aaron Gokaslan +3
Synthetic data has become an important tool in the fine-tuning of language models to follow instructions and solve complex problems. Nevertheless, the majority of open data to date…
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…
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,…
WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild
Bill Yuchen Lin, Yuntian Deng, Khyathi Chandu +6
We introduce WildBench, an automated evaluation framework designed to benchmark large language models (LLMs) using challenging, real-world user queries. WildBench consists of 1,024…
Superlatives in Context: Modeling the Implicit Semantics of Superlatives
Valentina Pyatkin, Bonnie Webber, Ido Dagan +1
Superlatives are used to single out elements with a maximal/minimal property. Semantically, superlatives perform a set comparison: something (or some things) has the min/max proper…
RewardBench: Evaluating Reward Models for Language Modeling
Nathan Lambert, Valentina Pyatkin, Jacob Morrison +9
Reward models (RMs) are at the crux of successfully using RLHF to align pretrained models to human preferences, yet there has been relatively little study that focuses on evaluatio…
Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language Models
Paul Röttger, Valentin Hofmann, Valentina Pyatkin +4
Much recent work seeks to evaluate values and opinions in large language models (LLMs) using multiple-choice surveys and questionnaires. Most of this work is motivated by concerns…
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…
Promptly Predicting Structures: The Return of Inference
Maitrey Mehta, Valentina Pyatkin, Vivek Srikumar
Prompt-based methods have been used extensively across NLP to build zero- and few-shot label predictors. Many NLP tasks are naturally structured: that is, their outputs consist of…
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…
What Makes it Ok to Set a Fire? Iterative Self-distillation of Contexts and Rationales for Disambiguating Defeasible Social and Moral Situations
Kavel Rao, Liwei Jiang, Valentina Pyatkin +5
Moral or ethical judgments rely heavily on the specific contexts in which they occur. Understanding varying shades of defeasible contextualizations (i.e., additional information th…