Search Results for author:
Found 12 papers, 3 papers with code
Long-form factuality in large language models
Empirically, we demonstrate that LLM agents can outperform crowdsourced human annotators - on a set of ~16k individual facts, SAFE agrees with crowdsourced human annotators 72% of the time, and on a random subset of 100 disagreement cases, SAFE wins 76% of the time.
Simple synthetic data reduces sycophancy in large language models
Adding these data in a lightweight finetuning step can significantly reduce sycophantic behavior on held-out prompts.
Deep Learning Methods for Device Identification Using Symbols Trace Plot
Devices authentication is one crucial aspect of any communication system.
Brainformers: Trading Simplicity for Efficiency
Using this insight, we develop a complex block, named Brainformer, that consists of a diverse sets of layers such as sparsely gated feed-forward layers, dense feed-forward layers, attention layers, and various forms of layer normalization and activation functions.
Symbol tuning improves in-context learning in language models
We present symbol tuning - finetuning language models on in-context input-label pairs where natural language labels (e. g., "positive/negative sentiment") are replaced with arbitrary symbols (e. g., "foo/bar").
Larger language models do in-context learning differently
We next study semantically-unrelated label ICL (SUL-ICL), in which labels are semantically unrelated to their inputs (e. g., foo/bar instead of negative/positive), thereby forcing language models to learn the input-label mappings shown in in-context exemplars in order to perform the task.
Symbolic Discovery of Optimization Algorithms
On diffusion models, Lion outperforms Adam by achieving a better FID score and reducing the training compute by up to 2. 3x.
On the Factory Floor: ML Engineering for Industrial-Scale Ads Recommendation Models
For industrial-scale advertising systems, prediction of ad click-through rate (CTR) is a central problem.
TabNAS: Rejection Sampling for Neural Architecture Search on Tabular Datasets
The best neural architecture for a given machine learning problem depends on many factors: not only the complexity and structure of the dataset, but also on resource constraints including latency, compute, energy consumption, etc.
PatentNet: A Large-Scale Incomplete Multiview, Multimodal, Multilabel Industrial Goods Image Database
In deep learning area, large-scale image datasets bring a breakthrough in the success of object recognition and retrieval.
Rethinking Co-design of Neural Architectures and Hardware Accelerators
In our work, we target the optimization of hardware and software configurations on an industry-standard edge accelerator.
Neural Phrase-to-Phrase Machine Translation
We also design an efficient dynamic programming algorithm to decode segments that allows the model to be trained faster than the existing neural phrase-based machine translation method by Huang et al. (2018).
