While standard IR models are primarily designed to optimize relevance, real-world search often needs to balance additional objectives such as diversity and fairness. These objectives depend on inter-document interactions and are commonly addressed using post-hoc heuristics or supervised learning methods, which require task-specific training for each ranking scenario and dataset. In this work, we propose an in-context learning (ICL) approach for listwise LLM rerankers that eliminates the need for such training. Instead, our method relies on a small number of example rankings that demonstrate the desired trade-offs between objectives for past queries similar to the current input. We evaluate our approach on common IR test collections to investigate multiple auxiliary objectives: group fairness (TREC Fairness), polarity diversity (Touché), and topical diversity (TREC Deep Learning 2019/2020). We empirically validate that our method enables control over ranking behavior through demonstration engineering, allowing nuanced behavioral adjustments without explicit optimization. Our experiment demonstrates significant improvements in auxiliary objectives, with up to 23% in topical diversity and 20.6% fairness gains across different tasks, while maintaining relevance across benchmarks.

A supervised ranking model, despite its effectiveness over traditional approaches, usually involves complex processing - typically multiple stages of task-specific pre-training and fine-tuning. This has motivated researchers to explore simpler pipelines leveraging large language models (LLMs) that can work in a zero-shot manner. However, since zero-shot inference does not make use of a training set of pairs of queries and their relevant documents, its performance is mostly worse than that of supervised models, which are trained on such example pairs. Motivated by the existing findings that training examples generally improve zero-shot performance, in our work, we explore if this also applies to ranking models. More specifically, given a query and a pair of documents, the preference prediction task is improved by augmenting examples of preferences for similar queries from a training set. Our proposed pairwise few-shot ranker demonstrates consistent improvements over the zero-shot baseline on both in-domain (TREC DL) and out-domain (BEIR subset) retrieval benchmarks.

In recent years, research shows that neural ranking models (NRMs) substantially outperform their lexical counterparts in text retrieval. In traditional search pipelines, a combination of features leads to well-defined behaviour. However, as neural approaches become increasingly prevalent as the final scoring component of engines or as standalone systems, their robustness to malicious text and, more generally, semantic perturbation needs to be better understood. We posit that the transformer attention mechanism can induce exploitable defects in search models through sensitivity to token position within a sequence, leading to an attack that could generalise beyond a single query or topic. We demonstrate such defects by showing that non-relevant text–such as promotional content–can be easily injected into a document without adversely affecting its position in search results. Unlike previous gradient-based attacks, we demonstrate the existence of these biases in a query-agnostic fashion. In doing so, without the knowledge of topicality, we can still reduce the negative effects of non-relevant content injection by controlling injection position. Our experiments are conducted with simulated on-topic promotional text automatically generated by prompting LLMs with topical context from target documents. We find that contextualisation of a non-relevant text further reduces negative effects whilst likely circumventing existing content filtering mechanisms. In contrast, lexical models are found to be more resilient to such content injection attacks. We then investigate a simple yet effective compensation for the weaknesses of the NRMs in search, validating our hypotheses regarding transformer bias.