相关论文: Exploiting Positional Bias for Query-Agnostic Gene…

When answering user queries, LLMs often retrieve knowledge from external sources stored in retrieval-augmented generation (RAG) databases. These are often populated from unvetted sources, e.g. the open web, and can contain maliciously…

Adversarial text attacks remain a persistent threat to transformer models, yet existing defenses are typically attack-specific or require costly model retraining, leaving a gap for attack-agnostic detection. We introduce Guided Perturbation…

Embedding models are crucial for tasks in Information Retrieval (IR) and semantic similarity measurement, yet their handling of longer texts and associated positional biases remains underexplored. In this study, we investigate the impact of…

Retrieval-Augmented Generation (RAG) has become a widely adopted approach to enhance Large Language Models (LLMs) by incorporating external knowledge and reducing hallucinations. However, noisy or irrelevant documents are often introduced…

There has been recently a growing interest in studying adversarial examples on natural language models in the black-box setting. These methods attack natural language classifiers by perturbing certain important words until the classifier…

Large Language Models (LLMs) are increasingly used in applications where the model selects from competing third-party content, such as in LLM-powered search engines or chatbot plugins. In this paper, we introduce Preference Manipulation…

Neural ranking models (NRMs) have been shown to be highly effective in terms of retrieval performance. Unfortunately, they have also displayed a higher degree of sensitivity to attacks than previous generation models. To help expose and…

Position bias has proven to be a prevalent issue of modern language models (LMs), where the models prioritize content based on its position within the given context. This bias often leads to unexpected model failures and hurts performance,…

It is known that neural networks are subject to attacks through adversarial perturbations, i.e., inputs which are maliciously crafted through perturbations to induce wrong predictions. Furthermore, such attacks are impossible to eliminate,…

Recently, the emergence of large language models (LLMs) has revolutionized the paradigm of information retrieval (IR) applications, especially in web search, by generating vast amounts of human-like texts on the Internet. As a result, IR…

Argument mining is a core technology for automating argument search in large document collections. Despite its usefulness for this task, most current approaches to argument mining are designed for use only with specific text types and fall…

Recent studies have highlighted the significant potential of Large Language Models (LLMs) as zero-shot relevance rankers. These methods predominantly utilize prompt learning to assess the relevance between queries and documents by…

With the advancement of generation models, AI-generated content (AIGC) is becoming more realistic, flooding the Internet. A recent study suggests that this phenomenon causes source bias in text retrieval for web search. Specifically, neural…

Recent advances in unbiased learning to rank (LTR) count on Inverse Propensity Scoring (IPS) to eliminate bias in implicit feedback. Though theoretically sound in correcting the bias introduced by treating clicked documents as relevant, IPS…

The increasing integration of Large Language Model (LLM) based search engines has transformed the landscape of information retrieval. However, these systems are vulnerable to adversarial attacks, especially ranking manipulation attacks,…

Recent advances in large reasoning models (LRMs) have enabled remarkable performance on complex tasks such as mathematics and coding by generating long Chain-of-Thought (CoT) traces. In this paper, we identify and systematically analyze a…

Neural ranking models (NRMs) have shown great success in information retrieval (IR). But their predictions can easily be manipulated using adversarial examples, which are crafted by adding imperceptible perturbations to legitimate…

We propose the Neural Vector Space Model (NVSM), a method that learns representations of documents in an unsupervised manner for news article retrieval. In the NVSM paradigm, we learn low-dimensional representations of words and documents…

Natural Language Processing (NLP) models based on Machine Learning (ML) are susceptible to adversarial attacks -- malicious algorithms that imperceptibly modify input text to force models into making incorrect predictions. However,…

In web search and recommendation systems, user clicks are widely used to train ranking models. However, click data is heavily biased, i.e., users tend to click higher-ranked items (position bias), choose only what was shown to them…