Search Results for author:
Found 38 papers, 26 papers with code
A Call for Collaborative Intelligence: Why Human-Agent Systems Should Precede AI Autonomy
This paper argues that progress in AI should not be measured by how independent systems become, but by how well they can work with humans.
Mark Your LLM: Detecting the Misuse of Open-Source Large Language Models via Watermarking
Our experiments reveal that backdoor watermarking could effectively detect IP Violation, while inference-time watermark distillation is applicable in both scenarios but less robust to further fine-tuning and has a more significant impact on LLM performance compared to backdoor watermarking.
Scaling Laws for Many-Shot In-Context Learning with Self-Generated Annotations
The high cost of obtaining high-quality annotated data for in-context learning (ICL) has motivated the development of methods that use self-generated annotations in place of ground-truth labels.
TabGen-ICL: Residual-Aware In-Context Example Selection for Tabular Data Generation
We demonstrate for the first time that prompting a fixed LLM can yield high-quality synthetic tabular data.
Can LLM Watermarks Robustly Prevent Unauthorized Knowledge Distillation?
The radioactive nature of Large Language Model (LLM) watermarking enables the detection of watermarks inherited by student models when trained on the outputs of watermarked teacher models, making it a promising tool for preventing unauthorized knowledge distillation.
Cold-Start Recommendation towards the Era of Large Language Models (LLMs): A Comprehensive Survey and Roadmap
Cold-start problem is one of the long-standing challenges in recommender systems, focusing on accurately modeling new or interaction-limited users or items to provide better recommendations.
Exploring Response Uncertainty in MLLMs: An Empirical Evaluation under Misleading Scenarios
By calculating the misleading rate, and capturing both correct-to-incorrect and incorrect-to-correct shifts between the two sets of responses, we can effectively metric the model's response uncertainty.
Less is More: Extreme Gradient Boost Rank-1 Adaption for Efficient Finetuning of LLMs
This work advances parameter-efficient fine-tuning for LLMs, and offers a promising solution for adapting LLMs to downstream tasks while optimizing performance and efficiency.
Mitigating Modality Prior-Induced Hallucinations in Multimodal Large Language Models via Deciphering Attention Causality
These biases arise from the visual encoder and the Large Language Model (LLM) backbone, affecting the attention mechanism responsible for aligning multimodal inputs.
Recent Advances of Multimodal Continual Learning: A Comprehensive Survey
Continual learning (CL) aims to empower machine learning models to learn continually from new data, while building upon previously acquired knowledge without forgetting.
TIS-DPO: Token-level Importance Sampling for Direct Preference Optimization With Estimated Weights
In this work, we propose that the optimal data for DPO has equal expected rewards for each token in winning and losing responses, as there is no difference in token importance.
Can Watermarked LLMs be Identified by Users via Crafted Prompts?
Finally, we propose that the key to enhancing the imperceptibility of watermarked LLMs is to increase the randomness of watermark key selection.
Interpretable Contrastive Monte Carlo Tree Search Reasoning
Thus, we conducted extensive ablation studies and quantitative analysis on components of MCTS, revealing the impact of each component on the MCTS reasoning performance of LLMs.
WaterSeeker: Pioneering Efficient Detection of Watermarked Segments in Large Documents
Watermarking algorithms for large language models (LLMs) have attained high accuracy in detecting LLM-generated text.
Entropy-Based Decoding for Retrieval-Augmented Large Language Models
Augmenting Large Language Models (LLMs) with retrieved external knowledge has proven effective for improving the factual accuracy of generated responses.
Refiner: Restructure Retrieval Content Efficiently to Advance Question-Answering Capabilities
Experiments show that a trained $\textit{Refiner}$ (with 7B parameters) exhibits significant gain to downstream LLM in improving answer accuracy, and outperforms other state-of-the-art advanced RAG and concurrent compressing approaches in various single-hop and multi-hop QA tasks.
On the Robustness of Document-Level Relation Extraction Models to Entity Name Variations
To this end, we systematically investigate the robustness of DocRE models to entity name variations in this work.
MarkLLM: An Open-Source Toolkit for LLM Watermarking
However, the abundance of LLM watermarking algorithms, their intricate mechanisms, and the complex evaluation procedures and perspectives pose challenges for researchers and the community to easily experiment with, understand, and assess the latest advancements.
An Entropy-based Text Watermarking Detection Method
From the experiments, we demonstrate that our EWD can achieve better detection performance in low-entropy scenarios, and our method is also general and can be applied to texts with different entropy distributions.
ChatCite: LLM Agent with Human Workflow Guidance for Comparative Literature Summary
In this work, we firstly focus on the independent literature summarization step and introduce ChatCite, an LLM agent with human workflow guidance for comparative literature summary.
Can Watermarks Survive Translation? On the Cross-lingual Consistency of Text Watermark for Large Language Models
Furthermore, we analyze two key factors that contribute to the cross-lingual consistency in text watermarking and propose X-SIR as a defense method against CWRA.
Direct Large Language Model Alignment Through Self-Rewarding Contrastive Prompt Distillation
In this paper, we propose a method to evaluate the response preference by using the output probabilities of response pairs under contrastive prompt pairs, which could achieve better performance on LLaMA2-7B and LLaMA2-13B compared to RLAIF.
A Survey of Text Watermarking in the Era of Large Language Models
This paper conducts a comprehensive survey of the current state of text watermarking technology, covering four main aspects: (1) an overview and comparison of different text watermarking techniques; (2) evaluation methods for text watermarking algorithms, including their detectability, impact on text or LLM quality, robustness under target or untargeted attacks; (3) potential application scenarios for text watermarking technology; (4) current challenges and future directions for text watermarking.
Prompt Me Up: Unleashing the Power of Alignments for Multimodal Entity and Relation Extraction
Additionally, our method is orthogonal to previous multimodal fusions, and using it on prior SOTA fusions further improves 5. 47% F1.
RAPL: A Relation-Aware Prototype Learning Approach for Few-Shot Document-Level Relation Extraction
However, existing works often struggle to obtain class prototypes with accurate relational semantics: 1) To build prototype for a target relation type, they aggregate the representations of all entity pairs holding that relation, while these entity pairs may also hold other relations, thus disturbing the prototype.
A Semantic Invariant Robust Watermark for Large Language Models
In this work, we propose a semantic invariant watermarking method for LLMs that provides both attack robustness and security robustness.
An Unforgeable Publicly Verifiable Watermark for Large Language Models
Experiments demonstrate that our algorithm attains high detection accuracy and computational efficiency through neural networks.
Exploring the Compositional Generalization in Context Dependent Text-to-SQL Parsing
Based on these observations, we propose a method named \texttt{p-align} to improve the compositional generalization of Text-to-SQL models.
GDA: Generative Data Augmentation Techniques for Relation Extraction Tasks
These techniques neither preserve the semantic consistency of the original sentences when rule-based augmentations are adopted, nor preserve the syntax structure of sentences when expressing relations using seq2seq models, resulting in less diverse augmentations.
Enhancing Cross-lingual Natural Language Inference by Soft Prompting with Multilingual Verbalizer
In this paper, we propose a novel Soft prompt learning framework with the Multilingual Verbalizer (SoftMV) for XNLI.
Cross-Lingual Natural Language Inference
Cross-Lingual Transfer
+1
Gaussian Prior Reinforcement Learning for Nested Named Entity Recognition
Existing works for nested NER ignore the recognition order and boundary position relation of nested entities.
A comprehensive evaluation of ChatGPT's zero-shot Text-to-SQL capability
This paper presents the first comprehensive analysis of ChatGPT's Text-to-SQL ability.
Character-level White-Box Adversarial Attacks against Transformers via Attachable Subwords Substitution
We propose the first character-level white-box adversarial attack method against transformer models.
Entity-to-Text based Data Augmentation for various Named Entity Recognition Tasks
Data augmentation techniques have been used to alleviate the problem of scarce labeled data in various NER tasks (flat, nested, and discontinuous NER tasks).
Semantic Enhanced Text-to-SQL Parsing via Iteratively Learning Schema Linking Graph
First, we extract a schema linking graph from PLMs through a probing procedure in an unsupervised manner.
CHEF: A Pilot Chinese Dataset for Evidence-Based Fact-Checking
The explosion of misinformation spreading in the media ecosystem urges for automated fact-checking.
A Multi-level Supervised Contrastive Learning Framework for Low-Resource Natural Language Inference
Natural Language Inference (NLI) is a growingly essential task in natural language understanding, which requires inferring the relationship between the sentence pairs (premise and hypothesis).
