Search Results for author:
Found 11 papers, 5 papers with code
On the Vulnerability of Applying Retrieval-Augmented Generation within Knowledge-Intensive Application Domains
To understand this vulnerability, we discovered that the deviation from the query's embedding to that of the poisoned document tends to follow a pattern in which the high similarity between the poisoned document and the query is retained, thereby enabling precise retrieval.
Open-world Multi-label Text Classification with Extremely Weak Supervision
We study open-world multi-label text classification under extremely weak supervision (XWS), where the user only provides a brief description for classification objectives without any labels or ground-truth label space.
Argument-Aware Approach To Event Linking
Event linking connects event mentions in text with relevant nodes in a knowledge base (KB).
Characterizing Truthfulness in Large Language Model Generations with Local Intrinsic Dimension
We study how to characterize and predict the truthfulness of texts generated from large language models (LLMs), which serves as a crucial step in building trust between humans and LLMs.
Middleware for LLMs: Tools Are Instrumental for Language Agents in Complex Environments
The applications of large language models (LLMs) have expanded well beyond the confines of text processing, signaling a new era where LLMs are envisioned as generalist language agents capable of operating within complex real-world environments.
Answer is All You Need: Instruction-following Text Embedding via Answering the Question
This work aims to build a text embedder that can capture characteristics of texts specified by user instructions.
RAW: A Robust and Agile Plug-and-Play Watermark Framework for AI-Generated Images with Provable Guarantees
Subsequently, we employ a classifier that is jointly trained with the watermark to detect the presence of the watermark.
Demystifying Poisoning Backdoor Attacks from a Statistical Perspective
The growing dependence on machine learning in real-world applications emphasizes the importance of understanding and ensuring its safety.
Text-to-SQL Error Correction with Language Models of Code
Thus, we propose a novel representation for SQL queries and their edits that adheres more closely to the pre-training corpora of language models of code.
A Retrieve-and-Read Framework for Knowledge Graph Link Prediction
To address the limitations of existing KG link prediction frameworks, we propose a novel retrieve-and-read framework, which first retrieves a relevant subgraph context for the query and then jointly reasons over the context and the query with a high-capacity reader.
Ranked #2 on
Link Prediction
on FB15k-237
A Metamodel and Framework for Artificial General Intelligence From Theory to Practice
This paper introduces a new metamodel-based knowledge representation that significantly improves autonomous learning and adaptation.
