Search Results for author:
Found 8 papers, 6 papers with code
Data Contamination Report from the 2024 CONDA Shared Task
The workshop fostered a shared task to collect evidence on data contamination in current available datasets and models.
OlympicArena: Benchmarking Multi-discipline Cognitive Reasoning for Superintelligent AI
We delve into the models' cognitive reasoning abilities, their performance across different modalities, and their outcomes in process-level evaluations, which are vital for tasks requiring complex reasoning with lengthy solutions.
Benchmarking Benchmark Leakage in Large Language Models
By analyzing 31 LLMs under the context of mathematical reasoning, we reveal substantial instances of training even test set misuse, resulting in potentially unfair comparisons.
Reformatted Alignment
This paper explores elevating the quality of existing instruction data to better align with human values, introducing a simple and effective approach named ReAlign, which reformats the responses of instruction data into a format that better aligns with pre-established criteria and the collated evidence.
RIGHT: Retrieval-augmented Generation for Mainstream Hashtag Recommendation
Automatic mainstream hashtag recommendation aims to accurately provide users with concise and popular topical hashtags before publication.
Merging Experts into One: Improving Computational Efficiency of Mixture of Experts
Although a sparse Mixture of Experts (MoE) can reduce the cost by activating a small subset of parameters (e. g., one expert) for each input, its computation escalates significantly if increasing the number of activated experts, limiting its practical utility.
Generative Judge for Evaluating Alignment
The rapid development of Large Language Models (LLMs) has substantially expanded the range of tasks they can address.
MerA: Merging Pretrained Adapters For Few-Shot Learning
Adapter tuning, which updates only a few parameters, has become a mainstream method for fine-tuning pretrained language models to downstream tasks.
