Search Results for author:
Found 33 papers, 23 papers with code
Beyond Training: Dynamic Token Merging for Zero-Shot Video Understanding
Recent advancements in multimodal large language models (MLLMs) have opened new avenues for video understanding.
CBT-Bench: Evaluating Large Language Models on Assisting Cognitive Behavior Therapy
There is a significant gap between patient needs and available mental health support today.
MMSci: A Dataset for Graduate-Level Multi-Discipline Multimodal Scientific Understanding
The results highlight the high difficulty of these tasks and the significant performance gap among models.
MultiAgent Collaboration Attack: Investigating Adversarial Attacks in Large Language Model Collaborations via Debate
Large Language Models (LLMs) have shown exceptional results on current benchmarks when working individually.
DALD: Improving Logits-based Detector without Logits from Black-box LLMs
However, these methods grapple with the misalignment between the distributions of the surrogate and the often undisclosed target models, leading to performance degradation, particularly with the introduction of new, closed-source models.
Unveiling the Impact of Coding Data Instruction Fine-Tuning on Large Language Models Reasoning
First, coding data tuning enhances the overall reasoning capabilities of LLMs across different model families and scales.
A Survey on Large Language Models for Critical Societal Domains: Finance, Healthcare, and Law
In the fast-evolving domain of artificial intelligence, large language models (LLMs) such as GPT-3 and GPT-4 are revolutionizing the landscapes of finance, healthcare, and law: domains characterized by their reliance on professional expertise, challenging data acquisition, high-stakes, and stringent regulatory compliance.
Introducing v0.5 of the AI Safety Benchmark from MLCommons
We created a new taxonomy of 13 hazard categories, of which 7 have tests in the v0. 5 benchmark.
Unveiling the Misuse Potential of Base Large Language Models via In-Context Learning
The open-sourcing of large language models (LLMs) accelerates application development, innovation, and scientific progress.
A Safe Harbor for AI Evaluation and Red Teaming
Independent evaluation and red teaming are critical for identifying the risks posed by generative AI systems.
A Self-supervised Pressure Map human keypoint Detection Approch: Optimizing Generalization and Computational Efficiency Across Datasets
In environments where RGB images are inadequate, pressure maps is a viable alternative, garnering scholarly attention.
Test-Time Backdoor Attacks on Multimodal Large Language Models
Backdoor attacks are commonly executed by contaminating training data, such that a trigger can activate predetermined harmful effects during the test phase.
TrustAgent: Towards Safe and Trustworthy LLM-based Agents
The rise of LLM-based agents shows great potential to revolutionize task planning, capturing significant attention.
Navigating the OverKill in Large Language Models
Large language models are meticulously aligned to be both helpful and harmless.
Weak-to-Strong Jailbreaking on Large Language Models
In this paper, we propose the weak-to-strong jailbreaking attack, an efficient method to attack aligned LLMs to produce harmful text.
PLLaMa: An Open-source Large Language Model for Plant Science
Large Language Models (LLMs) have exhibited remarkable capabilities in understanding and interacting with natural language across various sectors.
Quokka: An Open-source Large Language Model ChatBot for Material Science
This paper presents the development of a specialized chatbot for materials science, leveraging the Llama-2 language model, and continuing pre-training on the expansive research articles in the materials science domain from the S2ORC dataset.
A Survey on Detection of LLMs-Generated Content
The burgeoning capabilities of advanced large language models (LLMs) such as ChatGPT have led to an increase in synthetic content generation with implications across a variety of sectors, including media, cybersecurity, public discourse, and education.
AlpaCare:Instruction-tuned Large Language Models for Medical Application
Instruction-finetuning (IFT) has become crucial in aligning Large Language Models (LLMs) with diverse human needs and has shown great potential in medical applications.
TRACE: A Comprehensive Benchmark for Continual Learning in Large Language Models
In this paper, we introduce TRACE, a novel benchmark designed to evaluate continual learning in LLMs.
Zero-Shot Detection of Machine-Generated Codes
We then modify the previous zero-shot text detection method, DetectGPT (Mitchell et al., 2023) by utilizing a surrogate white-box model to estimate the probability of the rightmost tokens, allowing us to identify code snippets generated by language models.
Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models
This study serves as a clarion call for a collective effort to overhaul and fortify the safety of open-source LLMs against malicious attackers.
PrivacyMind: Large Language Models Can Be Contextual Privacy Protection Learners
To address this challenge, we introduce Contextual Privacy Protection Language Models (PrivacyMind), a novel paradigm for fine-tuning LLMs that effectively injects domain-specific knowledge while safeguarding inference-time data privacy.
DNA-GPT: Divergent N-Gram Analysis for Training-Free Detection of GPT-Generated Text
However, this progress also presents a significant challenge in detecting the origin of a given text, and current research on detection methods lags behind the rapid evolution of LLMs.
Enhancing Small Medical Learners with Privacy-preserving Contextual Prompting
Although offering improved data privacy protection, domain-specific small language models (SLMs) often underperform LLMs, emphasizing the need for methods that reduce this performance gap while alleviating privacy concerns.
LLMScore: Unveiling the Power of Large Language Models in Text-to-Image Synthesis Evaluation
Existing automatic evaluation on text-to-image synthesis can only provide an image-text matching score, without considering the object-level compositionality, which results in poor correlation with human judgments.
Dynamic Prompting: A Unified Framework for Prompt Tuning
Experimental results underscore the significant performance improvement achieved by dynamic prompt tuning across a wide range of tasks, including NLP tasks, vision recognition tasks, and vision-language tasks.
Exploring the Limits of ChatGPT for Query or Aspect-based Text Summarization
Text summarization has been a crucial problem in natural language processing (NLP) for several decades.
MatKB: Semantic Search for Polycrystalline Materials Synthesis Procedures
In this paper, we present a novel approach to knowledge extraction and retrieval using Natural Language Processing (NLP) techniques for material science.
ReDi: Efficient Learning-Free Diffusion Inference via Trajectory Retrieval
Diffusion models show promising generation capability for a variety of data.
OASum: Large-Scale Open Domain Aspect-based Summarization
Specifically, zero/few-shot and fine-tuning results show that the model pre-trained on our corpus demonstrates a strong aspect or query-focused generation ability compared with the backbone model.
PcMSP: A Dataset for Scientific Action Graphs Extraction from Polycrystalline Materials Synthesis Procedure Text
Scientific action graphs extraction from materials synthesis procedures is important for reproducible research, machine automation, and material prediction.
Few-Shot Document-Level Event Argument Extraction
To fill this gap, we present FewDocAE, a Few-Shot Document-Level Event Argument Extraction benchmark, based on the existing document-level event extraction dataset.
Document-level Event Extraction
Event Argument Extraction
+2
