-
2024Trained on vast corpora of human language, language models demonstrate emergent human-like reasoning abilities. Yet they are still far from true intelligence, which opens up intriguing opportunities to explore the parallels of humans and model behaviors. In this work, we study the ability to skip steps in reasoning—a hallmark of human expertise developed through practice. Unlike humans, who may skip steps
-
2024Modern language models (LMs) need to follow human instructions while being faithful; yet, they often fail to achieve both. Here, we provide concrete evidence of a trade-off between instruction following (i.e., follow open-ended instructions) and faithfulness (i.e., ground responses in given context) when training LMs with these objectives. For instance, fine-tuning LLaMA-7B on instruction following datasets
-
2024Question answering based on retrieval-augmented generation (RAG-QA) is an important research topic in NLP and has a wide range of real-world applications. However, most existing datasets for this task are either constructed using a single source corpus or consist of short extractive answers, which fall short of evaluating large language model (LLM) based RAG-QA systems on cross-domain generalization. To
-
2024Learning of preference models from human feedback has been central to recent advances in artificial intelligence. Motivated by the cost of obtaining high-quality human annotations, we study efficient human preference elicitation for learning preference models. The key idea in our work is to generalize optimal designs, a methodology for computing optimal information-gathering policies, to questions with
-
2024Large language model advancements have enabled the development of multi-agent frameworks to tackle complex, real-world problems such as to automate tasks that require interactions with diverse tools, reasoning, and human collaboration. We present MARCO, a Multi-Agent Real-time Chat Orchestration framework for automating tasks using LLMs. MARCO addresses key challenges in utilizing LLMs for complex, multi-step
Related content
-
October 16, 2020New system is the first to use an attention-based sequence-to-sequence model, dispensing with separate models for features such as vibrato and phoneme durations.
-
October 15, 2020Hear Breen discuss his work leading research teams in speech synthesis and text-to-speech technologies, the science behind Alexa’s enhanced voice styles, and more.
-
October 05, 2020Challenge includes benchmark models from Amazon Alexa, which achieve state-of-the-art performance on five of the challenge tasks.
-
October 02, 2020Scientist leads team in London focused on improving voice-shopping experiences with Alexa.
-
September 28, 2020Hear Tur discuss his experience from his work on DARPA programs, how he’s seen the field of conversational AI evolve, and more.
-
September 24, 2020A combination of audio and visual signals guide the device’s movement, so the screen is always in view.