Search Results for author:
Found 7 papers, 4 papers with code
Legend: Leveraging Representation Engineering to Annotate Safety Margin for Preference Datasets
By leveraging this safety direction, Legend can then leverage the semantic distances of paired responses along this direction to annotate margins automatically.
Dishonesty in Helpful and Harmless Alignment
We find that this also induces dishonesty in helpful and harmless alignment where LLMs tell lies in generating harmless responses.
Empirical Study on Updating Key-Value Memories in Transformer Feed-forward Layers
The feed-forward networks (FFNs) in transformers are recognized as a group of key-value neural memories to restore abstract high-level knowledge.
See the Unseen: Better Context-Consistent Knowledge-Editing by Noises
In this paper, we empirically find that the effects of different contexts upon LLMs in recalling the same knowledge follow a Gaussian-like distribution.
Reconciliation of Pre-trained Models and Prototypical Neural Networks in Few-shot Named Entity Recognition
Incorporating large-scale pre-trained models with the prototypical neural networks is a de-facto paradigm in few-shot named entity recognition.
TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance
In this work, we extract samples from real financial reports to build a new large-scale QA dataset containing both Tabular And Textual data, named TAT-QA, where numerical reasoning is usually required to infer the answer, such as addition, subtraction, multiplication, division, counting, comparison/sorting, and the compositions.
Ranked #1 on
Question Answering
on TAT-QA
Lifelong Learning Process: Self-Memory Supervising and Dynamically Growing Networks
In this paper, we study how to solve these conflicts on generative models based on the conditional variational autoencoder(CVAE) model.
