Search Results for author:
Found 9 papers, 3 papers with code
Taxonomy, Opportunities, and Challenges of Representation Engineering for Large Language Models
We present the first comprehensive survey of RepE for LLMs, reviewing the rapidly growing literature to address key questions: What RepE methods exist and how do they differ?
Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs
In our experiment, a model is finetuned to output insecure code without disclosing this to the user.
Complete Implementation of WXF Chinese Chess Rules
Unlike repetitions in Western Chess where all repetitions are draws, repetitions in Chinese Chess could result in a win, draw, or loss depending on the kind of repetition being made by both players.
Study of the Proper NNUE Dataset
NNUE (Efficiently Updatable Neural Networks) has revolutionized chess engine development, with nearly all top engines adopting NNUE models to maintain competitive performance.
Analyzing the Generalization and Reliability of Steering Vectors
In this work, we rigorously investigate these properties, and show that steering vectors have substantial limitations both in- and out-of-distribution.
Low-Cost Generation and Evaluation of Dictionary Example Sentences
We introduce a new automatic evaluation metric called OxfordEval that measures the win-rate of generated sentences against existing Oxford Dictionary sentences.
Open RL Benchmark: Comprehensive Tracked Experiments for Reinforcement Learning
As a result, it is usually necessary to reproduce the experiments from scratch, which can be time-consuming and error-prone.
cDVGAN: One Flexible Model for Multi-class Gravitational Wave Signal and Glitch Generation
Specifically, our experiments show that training convolutional neural networks (CNNs) with our cDVGAN-generated data improves the detection of samples embedded in detector noise beyond the synthetic data from other state-of-the-art GAN models.
Ultra Violet radiation from sunlight: A key moderating factor in the spread of SARS-CoV-2 during the pandemic of 2020
The importance of UV radiation in natural sunlight as a disinfectant for SARS-CoV-2 cannot be ignored since the lockdowns were lifted; further, it can be considered as a factor for COVID management.
