1.1k citations
- Amazon (United States)US32 papers
- Carnegie Mellon UniversityUS8 papers
- Massachusetts Institute of TechnologyUS8 papers
- Microsoft Research (United Kingdom)GB8 papers
- Google (United States)US7 papers
- Johns Hopkins UniversityUS7 papers
- Meta (Israel)IL6 papers
- University of Maryland, College ParkUS6 papers
- California Southern UniversityUS5 papers
- University of California, Los AngelesUS5 papers
- University of OxfordGB5 papers
- University of Southern CaliforniaUS5 papers
111 papers · 1 filter
Beyond Perfect APIs: A Comprehensive Evaluation of LLM Agents Under Real-World API Complexity
Doyoung Kim, Zhiwei Ren, Jie Hao +11
We introduce WildAGTEval, a benchmark designed to evaluate large language model (LLM) agents' function-calling capabilities under realistic API complexity. Unlike prior work that a…
ReFactX: Scalable Reasoning with Reliable Facts via Constrained Generation
Riccardo Pozzi, Matteo Palmonari, Andrea Coletta +3
Knowledge gaps and hallucinations are persistent challenges for Large Language Models (LLMs), which generate unreliable responses when lacking the necessary information to fulfill…
Alexa Teacher Model: Pretraining and Distilling Multi-Billion-Parameter Encoders for Natural Language Understanding Systems
Jack FitzGerald, Shankar Ananthakrishnan, Konstantine Arkoudas +38
We present results from a large-scale experiment on pretraining encoders with non-embedding parameter counts ranging from 700M to 9.3B, their subsequent distillation into smaller m…
Supervised Graph Contrastive Pretraining for Text Classification
Samujjwal Ghosh, Subhadeep Maji, Maunendra Sankar Desarkar
Contrastive pretraining techniques for text classification has been largely studied in an unsupervised setting. However, oftentimes labeled data from related tasks which share labe…
Zero-Shot Open-Book Question Answering
Sia Gholami, Mehdi Noori
Open book question answering is a subset of question answering tasks where the system aims to find answers in a given set of documents (open-book) and common knowledge about a topi…
Kronecker Factorization for Preventing Catastrophic Forgetting in Large-scale Medical Entity Linking
Denis Jered McInerney, Luyang Kong, Kristjan Arumae +2
Multi-task learning is useful in NLP because it is often practically desirable to have a single model that works across a range of tasks. In the medical domain, sequential training…