Search Results for author:
Found 8 papers, 4 papers with code
TurtleBench: A Visual Programming Benchmark in Turtle Geometry
TurtleBench stands as one of the few benchmarks to evaluate the integration of visual understanding and code generation capabilities in LMMs, setting the stage for future research.
Nudging: Inference-time Alignment of LLMs via Guided Decoding
Building on this insight, nudging employs a small aligned model to generate nudging tokens to guide the base model's output during decoding when the base model's uncertainty is high.
Are Models Biased on Text without Gender-related Language?
A key observation in prior work is that models reinforce stereotypes as a consequence of the gendered correlations that are present in the training data.
EchoPrompt: Instructing the Model to Rephrase Queries for Improved In-context Learning
On average, EchoPrompt improves the Zero-shot-CoT performance of code-davinci-002 by 5% in numerical tasks and 13% in reading comprehension tasks.
Selective Perception: Optimizing State Descriptions with Reinforcement Learning for Language Model Actors
Large language models (LLMs) are being applied as actors for sequential decision making tasks in domains such as robotics and games, utilizing their general world knowledge and planning abilities.
A Theoretically Grounded Benchmark for Evaluating Machine Commonsense
Preliminary results suggest that the benchmark is challenging even for advanced language representation models designed for discriminative CSR question answering tasks.
Impact of Pretraining Term Frequencies on Few-Shot Reasoning
Pretrained Language Models (LMs) have demonstrated ability to perform numerical reasoning by extrapolating from a few examples in few-shot settings.
AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts
The remarkable success of pretrained language models has motivated the study of what kinds of knowledge these models learn during pretraining.
