163 citations · 372 across the 24 of their papers we have counts for
26 papers
Echoverse: Deep, Evolving Environments for Training Computer-Use Agents at Scale
Yash Pandya, Sahil Gupta, Sarthak Harne +10
Computer-use agents learn from what their actions change, so training one needs applications it can act on, break and reset. The applications that matter most are login-gated and s…
Fara-1.5: Scalable Learning Environments for Computer Use Agents
Ahmed Awadallah, Sahil Gupta, Yash Lara +12
Collecting computer use data from human demonstrations is expensive and slow, motivating the need for scalable generation strategies. This requires two key ingredients: environment…
The Art of Building Verifiers for Computer Use Agents
Corby Rosset, Pratyusha Sharma, Andrew Zhao +2
Verifying the success of computer use agent (CUA) trajectories is a critical challenge: without reliable verification, neither evaluation nor training signal can be trusted. In thi…
Fara-7B: An Efficient Agentic Model for Computer Use
Ahmed Awadallah, Yash Lara, Raghav Magazine +9
Progress in computer use agents (CUAs) has been constrained by the absence of large and high-quality datasets that capture how humans interact with a computer. While LLMs have thri…
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.…
Explorer: Scaling Exploration-driven Web Trajectory Synthesis for Multimodal Web Agents
Vardaan Pahuja, Yadong Lu, Corby Rosset +5
Recent success in large multimodal models (LMMs) has sparked promising applications of agents capable of autonomously completing complex web tasks. While open-source LMM agents hav…
LLM-Rubric: A Multidimensional, Calibrated Approach to Automated Evaluation of Natural Language Texts
Helia Hashemi, Jason Eisner, Corby Rosset +2
This paper introduces a framework for the automated evaluation of natural language texts. A manually constructed rubric describes how to assess multiple dimensions of interest. To…
AgentInstruct: Toward Generative Teaching with Agentic Flows
Arindam Mitra, Luciano Del Corro, Guoqing Zheng +11
Synthetic data is becoming increasingly important for accelerating the development of language models, both large and small. Despite several successful use cases, researchers also…
Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF
Tengyang Xie, Dylan J. Foster, Akshay Krishnamurthy +3
Reinforcement learning from human feedback (RLHF) has emerged as a central tool for language model alignment. We consider online exploration in RLHF, which exploits interactive acc…
MS MARCO Web Search: a Large-scale Information-rich Web Dataset with Millions of Real Click Labels
Qi Chen, Xiubo Geng, Corby Rosset +28
Recent breakthroughs in large models have highlighted the critical significance of data scale, labels and modals. In this paper, we introduce MS MARCO Web Search, the first large-s…
Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences
Corby Rosset, Ching-An Cheng, Arindam Mitra +3
This paper studies post-training large language models (LLMs) using preference feedback from a powerful oracle to help a model iteratively improve over itself. The typical approach…
Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
Marah Abdin, Jyoti Aneja, Hany Awadalla +126
We introduce phi-3-mini, a 3.8 billion parameter language model trained on 3.3 trillion tokens, whose overall performance, as measured by both academic benchmarks and internal test…
Researchy Questions: A Dataset of Multi-Perspective, Decompositional Questions for LLM Web Agents
Corby Rosset, Ho-Lam Chung, Guanghui Qin +5
Existing question answering (QA) datasets are no longer challenging to most powerful Large Language Models (LLMs). Traditional QA benchmarks like TriviaQA, NaturalQuestions, ELI5 a…
Orca-Math: Unlocking the potential of SLMs in Grade School Math
Arindam Mitra, Hamed Khanpour, Corby Rosset +1
Mathematical word problem-solving has long been recognized as a complex task for small language models (SLMs). A recent study hypothesized that the smallest model size, needed to a…
Axiomatic Preference Modeling for Longform Question Answering
Corby Rosset, Guoqing Zheng, Victor Dibia +2
The remarkable abilities of large language models (LLMs) like GPT-4 partially stem from post-training processes like Reinforcement Learning from Human Feedback (RLHF) involving hum…
Orca 2: Teaching Small Language Models How to Reason
Arindam Mitra, Luciano Del Corro, Shweti Mahajan +12
Orca 1 learns from rich signals, such as explanation traces, allowing it to outperform conventional instruction-tuned models on benchmarks like BigBench Hard and AGIEval. In Orca 2…
Overview of the TREC 2023 Product Product Search Track
Daniel Campos, Surya Kallumadi, Corby Rosset +2
This is the first year of the TREC Product search track. The focus this year was the creation of a reusable collection and evaluation of the impact of the use of metadata and multi…
Dodo: Dynamic Contextual Compression for Decoder-only LMs
Guanghui Qin, Corby Rosset, Ethan C. Chau +2
Transformer-based language models (LMs) are inefficient in long contexts. We propose Dodo, a solution for context compression. Instead of one vector per token in a standard transfo…
Automatic Pair Construction for Contrastive Post-training
Canwen Xu, Corby Rosset, Ethan C. Chau +6
Alignment serves as an important step to steer large language models (LLMs) towards human preferences. In this paper, we propose an automatic way to construct contrastive data for…
Zero-shot Clarifying Question Generation for Conversational Search
Zhenduo Wang, Yuancheng Tu, Corby Rosset +3
A long-standing challenge for search and conversational assistants is query intention detection in ambiguous queries. Asking clarifying questions in conversational search has been…
Augmenting Zero-Shot Dense Retrievers with Plug-in Mixture-of-Memories
Suyu Ge, Chenyan Xiong, Corby Rosset +3
In this paper we improve the zero-shot generalization ability of language models via Mixture-Of-Memory Augmentation (MoMA), a mechanism that retrieves augmentation documents from m…
Knowledge-Aware Language Model Pretraining
Corby Rosset, Chenyan Xiong, Minh Phan +3
How much knowledge do pretrained language models hold? Recent research observed that pretrained transformers are adept at modeling semantics but it is unclear to what degree they g…
Generic Intent Representation in Web Search
Hongfei Zhang, Xia Song, Chenyan Xiong +4
This paper presents GEneric iNtent Encoder (GEN Encoder) which learns a distributed representation space for user intent in search. Leveraging large scale user clicks from Bing sea…
Incorporating Query Term Independence Assumption for Efficient Retrieval and Ranking using Deep Neural Networks
Bhaskar Mitra, Corby Rosset, David Hawking +3
Classical information retrieval (IR) methods, such as query likelihood and BM25, score documents independently w.r.t. each query term, and then accumulate the scores. Assuming quer…