Claudia Hauff

The Disconnect Between Better Descriptive Reasoning Trace Quality and Recommendation Effectiveness

Gustavo Penha, Juan Elenter, Claudia Hauff, Hugues Bouchard et autres

Recent work has focused on improving explicit natural-language descriptive reasoning traces for generative recommendation. This includes systems that augment semantic ID (SID) prediction with chain-of-thought reasoning. However, because SIDs are opaque learned identifiers rather than natural language, they require costly alignment before …

As It Was: Aligning LLM Search Evaluation with Historical User Preferences

Ali Vardasbi, Gustavo Penha, Enrico Palumbo, Claudia Hauff et autres

Large-scale search systems evolve faster than human quality assurance scales, especially for long-tail intents and multilingual queries. LLM-as-a-judge approaches are a scalable alternative for evaluating the relevance of search engine result pages (SERPs), but judgments based solely on semantic similarity or world …

nl (code pays fourni par la source)

As It Was: Aligning LLM Search Evaluation with Historical User Preferences

Ali Vardasbi, Gustavo Penha, Enrico Palumbo, Claudia Hauff et autres

Large-scale search systems evolve faster than human quality assurance can scale, especially for long-tail intents and multilingual queries. LLM-as-a-judge approaches provide a scalable alternative for evaluating the relevance of search engine result pages (SERPs), but judgments based solely on semantic similarity or …

As It Was: Aligning LLM Search Evaluation with Historical User Preferences

Ali Vardasbi, Gustavo Penha, Enrico Palumbo, Claudia Hauff et autres

Large-scale search systems evolve faster than human quality assurance can scale, especially for long-tail intents and multilingual queries. LLM-as-a-judge approaches provide a scalable alternative for evaluating the relevance of search engine result pages (SERPs), but judgments based solely on semantic similarity or …

Report on the Search Futures Workshop at ECIR 2026

Leif Azzopardi, Charles L. A. Clarke, Claudia Hauff, Yubin Kim et autres

The Third Search Futures Workshop [Azzopardi et al., 2026], in conjunction with the Forty-eight European Conference on Information Retrieval (ECIR) 2026, looked into the future of search to ask questions such as: • How can we navigate data privacy in large language …

gb, ca, nl, us, au, de, cn, fi (code pays fourni par la source)

Same Outcomes, Different Journeys: A Trace-Level Framework for Comparing Human and GUI-Agent Behavior in Production Search Systems

Maria Movin, Claudia Hauff, Aron Henriksson, Panagiotis Papapetrou

LLM-driven GUI agents are increasingly used in production systems to automate workflows and simulate users for evaluation and optimization. Yet most GUI-agent evaluations emphasize task success and provide limited evidence on whether agents interact in human-like ways. We present a trace-level evaluation …

Same Outcomes, Different Journeys: A Trace-Level Framework for Comparing Human and GUI-Agent Behavior in Production Search Systems

Maria Movin, Claudia Hauff, Aron Henriksson, Panagiotis Papapetrou

LLM-driven GUI agents are increasingly used in production systems to automate workflows and simulate users for evaluation and optimization. Yet most GUI-agent evaluations emphasize task success and provide limited evidence on whether agents interact in human-like ways. We present a trace-level evaluation …

se (code pays fourni par la source)

Adaptive Repetition for Mitigating Position Bias in LLM-Based Ranking

Ali Vardasbi, Gustavo Penha, Claudia Hauff, Hugues Bouchard

nl (code pays fourni par la source)

The Third Search Futures Workshop at ECIR’26

Leif A. Azzopardi, Charles L. A. Clarke, Claudia Hauff, Yubin Kim et autres

gb, ca, nl, au, de (code pays fourni par la source)

Adaptive Repetition for Mitigating Position Bias in LLM-Based Ranking

Ali Vardasbi, Gustavo Penha, Claudia Hauff, Hugues Bouchard

When using LLMs to rank items based on given criteria, or evaluate answers, the order of candidate items can influence the model's final decision. This sensitivity to item positioning in a LLM's prompt is known as position bias. Prior research shows that …

Preaching to the ChoIR: Lessons IR Should Share with AI

Gianluca Demartini, Claudia Hauff, Matthew Lease, Stefano Mizzaro et autres

Contains fulltext : 321417.pdf (Publisher’s version ) (Open Access)

au, nl, us, it (code pays fourni par la source)

Zero-Shot Reranking with Large Language Models and Precomputed Ranking Features: Opportunities and Limitations

Maria Movin, Claudia Hauff

LLMs have been explored for their use in IR as end-to-end rankers, rerankers and assessors. Recently, the exploration of the prompt-and-predict paradigm for reranking in combination with highly performant LLMs have drawn the attention of researchers. Instead of training or fine-tuning a …

se (code pays fourni par la source)