Search Results for author:
Found 21 papers, 12 papers with code
Think Before Refusal : Triggering Safety Reflection in LLMs to Mitigate False Refusal Behavior
Recent advancements in large language models (LLMs) have demonstrated that fine-tuning and human alignment can render LLMs harmless.
ClusMFL: A Cluster-Enhanced Framework for Modality-Incomplete Multimodal Federated Learning in Brain Imaging Analysis
Building on this realistic simulation, we propose ClusMFL, a novel MFL framework that leverages feature clustering for cross-institutional brain imaging analysis under modality incompleteness.
Algorithmic Fidelity of Large Language Models in Generating Synthetic German Public Opinions: A Case Study
In recent research, large language models (LLMs) have been increasingly used to investigate public opinions.
Understanding When Tree of Thoughts Succeeds: Larger Models Excel in Generation, Not Discrimination
In this paper, we analyze the roles of the generator and discriminator separately to better understand the conditions when ToT is beneficial.
FedCCRL: Federated Domain Generalization with Cross-Client Representation Learning
Domain Generalization (DG) aims to train models that can effectively generalize to unseen domains.
DAMRO: Dive into the Attention Mechanism of LVLM to Reduce Object Hallucination
As we know, both the visual encoder and the Large Language Model (LLM) decoder in LVLMs are Transformer-based, allowing the model to extract visual information and generate text outputs via attention mechanisms.
Surgical, Cheap, and Flexible: Mitigating False Refusal in Language Models via Single Vector Ablation
We also show that our approach can be used for fine-grained calibration of model safety.
"Seeing the Big through the Small": Can LLMs Approximate Human Judgment Distributions on NLI from a Few Explanations?
This study proposes to exploit LLMs to approximate HJDs using a small number of expert labels and explanations.
The Potential and Challenges of Evaluating Attitudes, Opinions, and Values in Large Language Models
This paper aims to bridge this gap by providing a comprehensive overview of recent works on the evaluation of AOVs in LLMs.
FinerCut: Finer-grained Interpretable Layer Pruning for Large Language Models
Overparametrized transformer networks are the state-of-the-art architecture for Large Language Models (LLMs).
Look at the Text: Instruction-Tuned Language Models are More Robust Multiple Choice Selectors than You Think
We show that the text answers are more robust to question perturbations than the first token probabilities, when the first token answers mismatch the text answers.
On the Essence and Prospect: An Investigation of Alignment Approaches for Big Models
Big models have achieved revolutionary breakthroughs in the field of AI, but they might also pose potential concerns.
"My Answer is C": First-Token Probabilities Do Not Match Text Answers in Instruction-Tuned Language Models
The open-ended nature of language generation makes the evaluation of autoregressive large language models (LLMs) challenging.
ToViLaG: Your Visual-Language Generative Model is Also An Evildoer
Warning: this paper includes model outputs showing offensive content.
ACTOR: Active Learning with Annotator-specific Classification Heads to Embrace Human Label Variation
We show that in the active learning setting, a multi-head model performs significantly better than a single-head model in terms of uncertainty estimation.
Large-Scale and Multi-Perspective Opinion Summarization with Diverse Review Subsets
Furthermore, our in-depth analysis verifies that the advanced selection of review subsets and the two-stage training scheme are vital to boosting the summarization performance.
How to Distill your BERT: An Empirical Study on the Impact of Weight Initialisation and Distillation Objectives
To the best of our knowledge, this is the first work comprehensively evaluating distillation objectives in both settings.
CHAE: Fine-Grained Controllable Story Generation with Characters, Actions and Emotions
Story generation has emerged as an interesting yet challenging NLP task in recent years.
Open-domain Dialogue Generation Grounded with Dynamic Multi-form Knowledge Fusion
To merge these two forms of knowledge into the dialogue effectively, we design a dynamic virtual knowledge selector and a controller that help to enrich and expand knowledge space.
SceneFormer: Indoor Scene Generation with Transformers
In contrast, we do not use any appearance information, and implicitly learn object relations using the self-attention mechanism of transformers.
Controllable Multi-Character Psychology-Oriented Story Generation
In our work, we aim to design an emotional line for each character that considers multiple emotions common in psychological theories, with the goal of generating stories with richer emotional changes in the characters.
