12 papers · 1 filter
Seek: Self-Evaluative Exploration for Knowledge Retrieval
Amin Bigdeli, Radin Hamidi Rad, Negar Arabzadeh +4
LLM-based retrievers and rerankers have advanced passage ranking, yet both paradigms interact with the corpus in a single pass and commit to the resulting candidate set, leaving re…
Route Me If You Can: A Benchmark for Query Reformulation Selection
Hai Son Le, Negar Arabzadeh, Amin Bigdeli +4
LLM-based query reformulation can improve retrieval, but no single reformulation strategy is consistently optimal across queries, domains, retrievers, or model backbones. This crea…
EviQE: Evidence Selection for LLM-Based Query Expansion
Hai Son Le, Amin Bigdeli, Shirin Seyedsalehi +2
LLM-based query expansion increasingly conditions reformulation on documents retrieved from the target corpus, yet most work focuses on how to generate expansions rather than which…
ADORE: Iterative Query Expansion with Retrieval-Grounded Relevance Feedback
Amin Bigdeli, Negar Arabzadeh, Radin Hamidi Rad +3
LLM-based query expansion improves retrieval by enriching the original query with additional context. Yet most methods remain generation-driven, producing plausible pseudo-document…
Led to Mislead: Adversarial Content Injection for Attacks on Neural Ranking Models
Amin Bigdeli, Amir Khosrojerdi, Radin Hamidi Rad +3
Neural Ranking Models (NRMs) are central to modern information retrieval but remain highly vulnerable to adversarial manipulation. Existing attacks often rely on heuristics or surr…
A Reproducibility Study of LLM-Based Query Reformulation
Amin Bigdeli, Radin Hamidi Rad, Hai Son Le +4
Large Language Models (LLMs) are now widely used for query reformulation and expansion in Information Retrieval, with many studies reporting substantial effectiveness gains. Howeve…
ReFormeR: Learning and Applying Explicit Query Reformulation Patterns
Amin Bigdeli, Mert Incesu, Negar Arabzadeh +2
We present ReFormeR, a pattern-guided approach for query reformulation. Instead of prompting a language model to generate reformulations of a query directly, ReFormeR first elicits…
QueryGym: A Toolkit for Reproducible LLM-Based Query Reformulation
Amin Bigdeli, Radin Hamidi Rad, Mert Incesu +3
We present QueryGym, a lightweight, extensible Python toolkit that supports large language model (LLM)-based query reformulation. This is an important tool development since recent…
Evaluating the Robustness of Retrieval-Augmented Generation to Adversarial Evidence in the Health Domain
Shakiba Amirshahi, Amin Bigdeli, Charles L. A. Clarke +1
Retrieval augmented generation (RAG) systems provide a method for factually grounding the responses of a Large Language Model (LLM) by providing retrieved evidence, or context, as…
Adversarial Attacks against Neural Ranking Models via In-Context Learning
Amin Bigdeli, Negar Arabzadeh, Ebrahim Bagheri +1
While neural ranking models (NRMs) have shown high effectiveness, they remain susceptible to adversarial manipulation. In this work, we introduce Few-Shot Adversarial Prompting (FS…
EMPRA: Embedding Perturbation Rank Attack against Neural Ranking Models
Amin Bigdeli, Negar Arabzadeh, Ebrahim Bagheri +1
Recent research has shown that neural information retrieval techniques may be susceptible to adversarial attacks. Adversarial attacks seek to manipulate the ranking of documents, w…
Adapting Standard Retrieval Benchmarks to Evaluate Generated Answers
Negar Arabzadeh, Amin Bigdeli, Charles L. A. Clarke
Large language models can now directly generate answers to many factual questions without referencing external sources. Unfortunately, relatively little attention has been paid to…