Variations in Relevance Judgments and the Shelf Life of Test Collections

The fundamental property of Cranfield-style evaluations, that system rankings are stable even when assessors disagree on individual relevance decisions, was validated on traditional test collections. However, the paradigm shift towards neural retrieval models affected the characteristics of modern test collections, e.g., documents are short, judged with four grades of relevance, and information needs have no descriptions or narratives. Under these changes, it is unclear whether assessor disagreement remains negligible for system comparisons. We investigate this aspect under the additional condition that the few modern test collections are heavily re-used. Given more possible query interpretations due to less formalized information needs, an ''expiration date'' for test collections might be needed if top-effectiveness requires overfitting to a single interpretation of relevance. We run a reproducibility study and re-annotate the relevance judgments of the 2019 TREC Deep Learning track. We can reproduce prior work in the neural retrieval setting, showing that assessor disagreement does not affect system rankings. However, we observe that some models substantially degrade with our new relevance judgments, and some have already reached the effectiveness of humans as rankers, providing evidence that test collections can expire.

Counterfactual Query Rewriting to Use Historical Relevance Feedback

When a retrieval system receives a query it has encountered before, previous relevance feedback, such as clicks or explicit judgments can help to improve retrieval results. However, the content of a previously relevant document may have changed, or the document might not be available anymore. Despite this evolved corpus, we counterfactually use these previously relevant documents as relevance signals. In this paper we proposed approaches to rewrite user queries and compare them against a system that directly uses the previous qrels for the ranking. We expand queries with terms extracted from the previously relevant documents or derive so-called keyqueries that rank the previously relevant documents to the top of the current corpus. Our evaluation in the CLEF LongEval scenario shows that rewriting queries with historical relevance feedback improves the retrieval effectiveness and even outperforms computationally expensive transformer-based approaches.

Lightning IR: Straightforward Fine-tuning and Inference of Transformer-based Language Models for Information Retrieval

A wide range of transformer-based language models have been proposed for information retrieval tasks. However, fine-tuning and inference of these models is often complex and requires substantial engineering effort. This paper introduces Lightning IR, a PyTorch Lightning-based framework for fine-tuning and inference of transformer-based language models for information retrieval. Lightning IR provides a modular and extensible architecture that supports all stages of an information retrieval pipeline: from fine-tuning and indexing to searching and re-ranking. It is designed to be straightforward to use, scalable, and reproducible. Lightning IR is available as open-source: https://github.com/webis-de/lightning-ir.

Systematic Evaluation of Neural Retrieval Models on the Touché 2020 Argument Retrieval Subset of BEIR

The zero-shot effectiveness of neural retrieval models is often evaluated on the BEIR benchmark -- a combination of different IR evaluation datasets. Interestingly, previous studies found that particularly on the BEIR subset Touch\'e 2020, an argument retrieval task, neural retrieval models are considerably less effective than BM25. Still, so far, no further investigation has been conducted on what makes argument retrieval so "special". To more deeply analyze the respective potential limits of neural retrieval models, we run a reproducibility study on the Touch\'e 2020 data. In our study, we focus on two experiments: (i) a black-box evaluation (i.e., no model retraining), incorporating a theoretical exploration using retrieval axioms, and (ii) a data denoising evaluation involving post-hoc relevance judgments. Our black-box evaluation reveals an inherent bias of neural models towards retrieving short passages from the Touch\'e 2020 data, and we also find that quite a few of the neural models' results are unjudged in the Touch\'e 2020 data. As many of the short Touch\'e passages are not argumentative and thus non-relevant per se, and as the missing judgments complicate fair comparison, we denoise the Touch\'e 2020 data by excluding very short passages (less than 20 words) and by augmenting the unjudged data with post-hoc judgments following the Touch\'e guidelines. On the denoised data, the effectiveness of the neural models improves by up to 0.52 in nDCG@10, but BM25 is still more effective. Our code and the augmented Touch\'e 2020 dataset are available at \url{https://github.com/castorini/touche-error-analysis}.

A Systematic Investigation of Distilling Large Language Models into Cross-Encoders for Passage Re-ranking

Cross-encoders distilled from large language models are more effective re-rankers than cross-encoders fine-tuned using manually labeled data. However, the distilled models do not reach the language model's effectiveness. We construct and release a new distillation dataset, named Rank-DistiLLM, to investigate whether insights from fine-tuning cross-encoders on manually labeled data -- hard-negative sampling, deep sampling, and listwise loss functions -- are transferable to large language model ranker distillation. Our dataset can be used to train cross-encoders that reach the effectiveness of large language models while being orders of magnitude more efficient. Code and data is available at: https://github.com/webis-de/msmarco-llm-distillation

Set-Encoder: Permutation-Invariant Inter-Passage Attention for Listwise Passage Re-Ranking with Cross-Encoders

Cross-encoders are effective passage re-rankers. But when re-ranking multiple passages at once, existing cross-encoders inefficiently optimize the output ranking over several input permutations, as their passage interactions are not permutation-invariant. Moreover, their high memory footprint constrains the number of passages during listwise training. To tackle these issues, we propose the Set-Encoder, a new cross-encoder architecture that (1) introduces inter-passage attention with parallel passage processing to ensure permutation invariance between input passages, and that (2) uses fused-attention kernels to enable training with more passages at a time. In experiments on TREC Deep Learning and TIREx, the Set-Encoder is more effective than previous cross-encoders with a similar number of parameters. Compared to larger models, the Set-Encoder is more efficient and either on par or even more effective.

Analyzing Adversarial Attacks on Sequence-to-Sequence Relevance Models

Modern sequence-to-sequence relevance models like monoT5 can effectively capture complex textual interactions between queries and documents through cross-encoding. However, the use of natural language tokens in prompts, such as Query, Document, and Relevant for monoT5, opens an attack vector for malicious documents to manipulate their relevance score through prompt injection, e.g., by adding target words such as true. Since such possibilities have not yet been considered in retrieval evaluation, we analyze the impact of query-independent prompt injection via manually constructed templates and LLM-based rewriting of documents on several existing relevance models. Our experiments on the TREC Deep Learning track show that adversarial documents can easily manipulate different sequence-to-sequence relevance models, while BM25 (as a typical lexical model) is not affected. Remarkably, the attacks also affect encoder-only relevance models (which do not rely on natural language prompt tokens), albeit to a lesser extent.

Investigating the Effects of Sparse Attention on Cross-Encoders

Cross-encoders are effective passage and document re-rankers but less efficient than other neural or classic retrieval models. A few previous studies have applied windowed self-attention to make cross-encoders more efficient. However, these studies did not investigate the potential and limits of different attention patterns or window sizes. We close this gap and systematically analyze how token interactions can be reduced without harming the re-ranking effectiveness. Experimenting with asymmetric attention and different window sizes, we find that the query tokens do not need to attend to the passage or document tokens for effective re-ranking and that very small window sizes suffice. In our experiments, even windows of 4 tokens still yield effectiveness on par with previous cross-encoders while reducing the memory requirements to at most 78% / 41% and being 1% / 43% faster at inference time for passages / documents.

Evaluating Generative Ad Hoc Information Retrieval

Recent advances in large language models have enabled the development of viable generative information retrieval systems. A generative retrieval system returns a grounded generated text in response to an information need instead of the traditional document ranking. Quantifying the utility of these types of responses is essential for evaluating generative retrieval systems. As the established evaluation methodology for ranking-based ad hoc retrieval may seem unsuitable for generative retrieval, new approaches for reliable, repeatable, and reproducible experimentation are required. In this paper, we survey the relevant information retrieval and natural language processing literature, identify search tasks and system architectures in generative retrieval, develop a corresponding user model, and study its operationalization. This theoretical analysis provides a foundation and new insights for the evaluation of generative ad hoc retrieval systems.

The Information Retrieval Experiment Platform

We integrate ir_datasets, ir_measures, and PyTerrier with TIRA in the Information Retrieval Experiment Platform (TIREx) to promote more standardized, reproducible, scalable, and even blinded retrieval experiments. Standardization is achieved when a retrieval approach implements PyTerrier's interfaces and the input and output of an experiment are compatible with ir_datasets and ir_measures. However, none of this is a must for reproducibility and scalability, as TIRA can run any dockerized software locally or remotely in a cloud-native execution environment. Version control and caching ensure efficient (re)execution. TIRA allows for blind evaluation when an experiment runs on a remote server or cloud not under the control of the experimenter. The test data and ground truth are then hidden from public access, and the retrieval software has to process them in a sandbox that prevents data leaks. We currently host an instance of TIREx with 15 corpora (1.9 billion documents) on which 32 shared retrieval tasks are based. Using Docker images of 50 standard retrieval approaches, we automatically evaluated all approaches on all tasks (50 $\cdot$ 32 = 1,600~runs) in less than a week on a midsize cluster (1,620 CPU cores and 24 GPUs). This instance of TIREx is open for submissions and will be integrated with the IR Anthology, as well as released open source.