James Allan

Tanya Chowdhury, Razieh Rahimi, James Allan

Understanding why a model makes certain predictions is crucial when adapting it for real world decision making. LIME is a popular model-agnostic feature attribution method for the tasks of classification and regression. However, the task of learning to rank in information retrieval is more complex in comparison with either classification or regression. In this work, we extend LIME to propose Rank-LIME, a model-agnostic, local, post-hoc linear feature attribution method for the task of learning to rank that generates explanations for ranked lists. We employ novel correlation-based perturbations, differentiable ranking loss functions and introduce new metrics to evaluate ranking based additive feature attribution models. We compare Rank-LIME with a variety of competing systems, with models trained on the MS MARCO datasets and observe that Rank-LIME outperforms existing explanation algorithms in terms of Model Fidelity and Explain-NDCG. With this we propose one of the first algorithms to generate additive feature attributions for explaining ranked lists.

Zhiqi Huang, Puxuan Yu, James Allan

Benefiting from transformer-based pre-trained language models, neural ranking models have made significant progress. More recently, the advent of multilingual pre-trained language models provides great support for designing neural cross-lingual retrieval models. However, due to unbalanced pre-training data in different languages, multilingual language models have already shown a performance gap between high and low-resource languages in many downstream tasks. And cross-lingual retrieval models built on such pre-trained models can inherit language bias, leading to suboptimal result for low-resource languages. Moreover, unlike the English-to-English retrieval task, where large-scale training collections for document ranking such as MS MARCO are available, the lack of cross-lingual retrieval data for low-resource language makes it more challenging for training cross-lingual retrieval models. In this work, we propose OPTICAL: Optimal Transport distillation for low-resource Cross-lingual information retrieval. To transfer a model from high to low resource languages, OPTICAL forms the cross-lingual token alignment task as an optimal transport problem to learn from a well-trained monolingual retrieval model. By separating the cross-lingual knowledge from knowledge of query document matching, OPTICAL only needs bitext data for distillation training, which is more feasible for low-resource languages. Experimental results show that, with minimal training data, OPTICAL significantly outperforms strong baselines on low-resource languages, including neural machine translation.

Ali Montazeralghaem, James Allan

Conversational recommender systems (CRSs) are improving rapidly, according to the standard recommendation accuracy metrics. However, it is essential to make sure that these systems are robust in interacting with users including regular and malicious users who want to attack the system by feeding the system modified input data. In this paper, we propose an adversarial evaluation scheme including four scenarios in two categories and automatically generate adversarial examples to evaluate the robustness of these systems in the face of different input data. By executing these adversarial examples we can compare the ability of different conversational recommender systems to satisfy the user's preferences. We evaluate three CRSs by the proposed adversarial examples on two datasets. Our results show that none of these systems are robust and reliable to the adversarial examples.

Abhishek Madaan, Tanya Chowdhury, Neha Rana et al.

In this work, we explore various topics that fall under the umbrella of Uncertainty in post-hoc Explainable AI (XAI) methods. We in particular focus on the class of additive feature attribution explanation methods. We first describe our specifications of uncertainty and compare various statistical and recent methods to quantify the same. Next, for a particular instance, we study the relationship between a feature's attribution and its uncertainty and observe little correlation. As a result, we propose a modification in the distribution from which perturbations are sampled in LIME-based algorithms such that the important features have minimal uncertainty without an increase in computational cost. Next, while studying how the uncertainty in explanations varies across the feature space of a classifier, we observe that a fraction of instances show near-zero uncertainty. We coin the term "stable instances" for such instances and diagnose factors that make an instance stable. Next, we study how an XAI algorithm's uncertainty varies with the size and complexity of the underlying model. We observe that the more complex the model, the more inherent uncertainty is exhibited by it. As a result, we propose a measure to quantify the relative complexity of a blackbox classifier. This could be incorporated, for example, in LIME-based algorithms' sampling densities, to help different explanation algorithms achieve tighter confidence levels. Together, the above measures would have a strong impact on making XAI models relatively trustworthy for the end-user as well as aiding scientific discovery.

Nazanin Jafari, James Allan

Claim verification can be a challenging task. In this paper, we present a method to enhance the robustness and reasoning capabilities of automated claim verification through the extraction of short facts from evidence. Our novel approach, FactDetect, leverages Large Language Models (LLMs) to generate concise factual statements from evidence and label these facts based on their semantic relevance to the claim and evidence. The generated facts are then combined with the claim and evidence. To train a lightweight supervised model, we incorporate a fact-detection task into the claim verification process as a multitasking approach to improve both performance and explainability. We also show that augmenting FactDetect in the claim verification prompt enhances performance in zero-shot claim verification using LLMs. Our method demonstrates competitive results in the supervised claim verification model by 15% on the F1 score when evaluated for challenging scientific claim verification datasets. We also demonstrate that FactDetect can be augmented with claim and evidence for zero-shot prompting (AugFactDetect) in LLMs for verdict prediction. We show that AugFactDetect outperforms the baseline with statistical significance on three challenging scientific claim verification datasets with an average of 17.3% performance gain compared to the best performing baselines.

Nazanin Jafari, James Allan, Sheikh Muhammad Sarwar

Identifying the targets of hate speech is a crucial step in grasping the nature of such speech and, ultimately, in improving the detection of offensive posts on online forums. Much harmful content on online platforms uses implicit language especially when targeting vulnerable and protected groups such as using stereotypical characteristics instead of explicit target names, making it harder to detect and mitigate the language. In this study, we focus on identifying implied targets of hate speech, essential for recognizing subtler hate speech and enhancing the detection of harmful content on digital platforms. We define a new task aimed at identifying the targets even when they are not explicitly stated. To address that task, we collect and annotate target spans in three prominent implicit hate speech datasets: SBIC, DynaHate, and IHC. We call the resulting merged collection Implicit-Target-Span. The collection is achieved using an innovative pooling method with matching scores based on human annotations and Large Language Models (LLMs). Our experiments indicate that Implicit-Target-Span provides a challenging test bed for target span detection methods.

James Allan, Eunsol Choi, Daniel P. Lopresti et al.

In the fast-evolving field of information retrieval (IR), the integration of generative AI technologies such as large language models (LLMs) is transforming how users search for and interact with information. Recognizing this paradigm shift at the intersection of IR and generative AI (IR-GenAI), a visioning workshop supported by the Computing Community Consortium (CCC) was held in July 2024 to discuss the future of IR in the age of generative AI. This workshop convened 44 experts in information retrieval, natural language processing, human-computer interaction, and artificial intelligence from academia, industry, and government to explore how generative AI can enhance IR and vice versa, and to identify the major challenges and opportunities in this rapidly advancing field. This report contains a summary of discussions as potentially important research topics and contains a list of recommendations for academics, industry practitioners, institutions, evaluation campaigns, and funding agencies.

Atharva Nijasure, Tanya Chowdhury, James Allan

We conduct a behavioral exploration of LoRA fine-tuned LLMs for Passage Reranking to understand how relevance signals are learned and deployed by Large Language Models. By fine-tuning Mistral-7B, LLaMA3.1-8B, and Pythia-6.9B on MS MARCO under diverse LoRA configurations, we investigate how relevance modeling evolves across checkpoints, the impact of LoRA rank (1, 2, 8, 32), and the relative importance of updated MHA vs. MLP components. Our ablations reveal which layers and projections within LoRA transformations are most critical for reranking accuracy. These findings offer fresh explanations into LoRA's adaptation mechanisms, setting the stage for deeper mechanistic studies in Information Retrieval. All models used in this study have been shared.

Tanya Chowdhury, Yair Zick, James Allan

Numerous works propose post-hoc, model-agnostic explanations for learning to rank, focusing on ordering entities by their relevance to a query through feature attribution methods. However, these attributions often weakly correlate or contradict each other, confusing end users. We adopt an axiomatic game-theoretic approach, popular in the feature attribution community, to identify a set of fundamental axioms that every ranking-based feature attribution method should satisfy. We then introduce Rank-SHAP, extending classical Shapley values to ranking. We evaluate the RankSHAP framework through extensive experiments on two datasets, multiple ranking methods and evaluation metrics. Additionally, a user study confirms RankSHAP's alignment with human intuition. We also perform an axiomatic analysis of existing rank attribution algorithms to determine their compliance with our proposed axioms. Ultimately, our aim is to equip practitioners with a set of axiomatically backed feature attribution methods for studying IR ranking models, that ensure generality as well as consistency.

Nazanin Jafari, James Allan, Mohit Iyyer

Evaluating the factuality of long-form output generated by large language models (LLMs) remains challenging, particularly when responses are open-ended and contain many fine-grained factual statements. Existing evaluation methods primarily focus on precision: they decompose a response into atomic claims and verify each claim against external knowledge sources such as Wikipedia. However, this overlooks an equally important dimension of factuality: recall, whether the generated response covers the relevant facts that should be included. We propose a comprehensive factuality evaluation framework that jointly measures precision and recall. Our method leverages external knowledge sources to construct reference facts and determine whether they are captured in generated text. We further introduce an importance-aware weighting scheme based on relevance and salience. Our analysis reveals that current LLMs perform substantially better on precision than on recall, suggesting that factual incompleteness remains a major limitation of long-form generation and that models are generally better at covering highly important facts than the full set of relevant facts.

Tanya Chowdhury, Atharva Nijasure, James Allan

Transformer networks, particularly those achieving performance comparable to GPT models, are well known for their robust feature extraction abilities. However, the nature of these extracted features and their alignment with human-engineered ones remain unexplored. In this work, we investigate the internal mechanisms of state-of-the-art, fine-tuned LLMs for passage reranking. We employ a probing-based analysis to examine neuron activations in ranking LLMs, identifying the presence of known human-engineered and semantic features. Our study spans a broad range of feature categories, including lexical signals, document structure, query-document interactions, and complex semantic representations, to uncover underlying patterns influencing ranking decisions. Through experiments on four different ranking LLMs, we identify statistical IR features that are prominently encoded in LLM activations, as well as others that are notably missing. Furthermore, we analyze how these models respond to out-of-distribution queries and documents, revealing distinct generalization behaviors. By dissecting the latent representations within LLM activations, we aim to improve both the interpretability and effectiveness of ranking models. Our findings offer crucial insights for developing more transparent and reliable retrieval systems, and we release all necessary scripts and code to support further exploration.

Tanya Chowdhury, Atharva Nijasure, Yair Zick et al.

Fine-tuned Large Language Models (LLMs) encode rich task-specific features, but the form of these representations, especially within MLP layers, remains unclear. Empirical inspection of LoRA updates shows that new features concentrate in mid-layer MLPs, yet the scale of these layers obscures meaningful structure. Prior probing suggests that statistical priors may strengthen, split, or vanish across depth, motivating the need to study how neurons work together rather than in isolation. We introduce a mechanistic interpretability framework based on coalitional game theory, where neurons mimic agents in a hedonic game whose preferences capture their synergistic contributions to layer-local computations. Using top-responsive utilities and the PAC-Top-Cover algorithm, we extract stable coalitions of neurons: groups whose joint ablation has non-additive effects. We then track their transitions across layers as persistence, splitting, merging, or disappearance. Applied to LLaMA, Mistral, and Pythia rerankers fine-tuned on scalar IR tasks, our method finds coalitions with consistently higher synergy than clustering baselines. By revealing how neurons cooperate to encode features, hedonic coalitions uncover higher-order structure beyond disentanglement and yield computational units that are functionally important, interpretable, and predictive across domains.

Zhiqi Huang, Hansi Zeng, Hamed Zamani et al.

In this work, we explore a Multilingual Information Retrieval (MLIR) task, where the collection includes documents in multiple languages. We demonstrate that applying state-of-the-art approaches developed for cross-lingual information retrieval to MLIR tasks leads to sub-optimal performance. This is due to the heterogeneous and imbalanced nature of multilingual collections -- some languages are better represented in the collection and some benefit from large-scale training data. To address this issue, we present KD-SPD, a novel soft prompt decoding approach for MLIR that implicitly "translates" the representation of documents in different languages into the same embedding space. To address the challenges of data scarcity and imbalance, we introduce a knowledge distillation strategy. The teacher model is trained on rich English retrieval data, and by leveraging bi-text data, our distillation framework transfers its retrieval knowledge to the multilingual document encoder. Therefore, our approach does not require any multilingual retrieval training data. Extensive experiments on three MLIR datasets with a total of 15 languages demonstrate that KD-SPD significantly outperforms competitive baselines in all cases. We conduct extensive analyses to show that our method has less language bias and better zero-shot transfer ability towards new languages.

Razieh Rahimi, Youngwoo Kim, Hamed Zamani et al.

We present GenEx, a generative model to explain search results to users beyond just showing matches between query and document words. Adding GenEx explanations to search results greatly impacts user satisfaction and search performance. Search engines mostly provide document titles, URLs, and snippets for each result. Existing model-agnostic explanation methods similarly focus on word matching or content-based features. However, a recent user study shows that word matching features are quite obvious to users and thus of slight value. GenEx explains a search result by providing a terse description for the query aspect covered by that result. We cast the task as a sequence transduction problem and propose a novel model based on the Transformer architecture. To represent documents with respect to the given queries and yet not generate the queries themselves as explanations, two query-attention layers and masked-query decoding are added to the Transformer architecture. The model is trained without using any human-generated explanations. Training data are instead automatically constructed to ensure a tolerable noise level and a generalizable learned model. Experimental evaluation shows that our explanation models significantly outperform the baseline models. Evaluation through user studies also demonstrates that our explanation model generates short yet useful explanations.

Hamed Bonab, Mohammad Aliannejadi, Ali Vardasbi et al.

We study the problem of recommending relevant products to users in relatively resource-scarce markets by leveraging data from similar, richer in resource auxiliary markets. We hypothesize that data from one market can be used to improve performance in another. Only a few studies have been conducted in this area, partly due to the lack of publicly available experimental data. To this end, we collect and release XMarket, a large dataset covering 18 local markets on 16 different product categories, featuring 52.5 million user-item interactions. We introduce and formalize the problem of cross-market product recommendation, i.e., market adaptation. We explore different market-adaptation techniques inspired by state-of-the-art domain-adaptation and meta-learning approaches and propose a novel neural approach for market adaptation, named FOREC. Our model follows a three-step procedure -- pre-training, forking, and fine-tuning -- in order to fully utilize the data from an auxiliary market as well as the target market. We conduct extensive experiments studying the impact of market adaptation on different pairs of markets. Our proposed approach demonstrates robust effectiveness, consistently improving the performance on target markets compared to competitive baselines selected for our analysis. In particular, FOREC improves on average 24% and up to 50% in terms of nDCG@10, compared to the NMF baseline. Our analysis and experiments suggest specific future directions in this research area. We release our data and code for academic purposes.

Dong-Ho Lee, Ravi Kiran Selvam, Sheikh Muhammad Sarwar et al.

Deep neural models for named entity recognition (NER) have shown impressive results in overcoming label scarcity and generalizing to unseen entities by leveraging distant supervision and auxiliary information such as explanations. However, the costs of acquiring such additional information are generally prohibitive. In this paper, we present a novel two-stage framework (AutoTriggER) to improve NER performance by automatically generating and leveraging ``entity triggers'' which are human-readable cues in the text that help guide the model to make better decisions. Our framework leverages post-hoc explanation to generate rationales and strengthens a model's prior knowledge using an embedding interpolation technique. This approach allows models to exploit triggers to infer entity boundaries and types instead of solely memorizing the entity words themselves. Through experiments on three well-studied NER datasets, AutoTriggER shows strong label-efficiency, is capable of generalizing to unseen entities, and outperforms the RoBERTa-CRF baseline by nearly 0.5 F1 points on average.

Youngwoo Kim, Razieh Rahimi, Hamed Bonab et al.

Transformer-based rankers have shown state-of-the-art performance. However, their self-attention operation is mostly unable to process long sequences. One of the common approaches to train these rankers is to heuristically select some segments of each document, such as the first segment, as training data. However, these segments may not contain the query-related parts of documents. To address this problem, we propose query-driven segment selection from long documents to build training data. The segment selector provides relevant samples with more accurate labels and non-relevant samples which are harder to be predicted. The experimental results show that the basic BERT-based ranker trained with the proposed segment selector significantly outperforms that trained by the heuristically selected segments, and performs equally to the state-of-the-art model with localized self-attention that can process longer input sequences. Our findings open up new direction to design efficient transformer-based rankers.

Zhiqi Huang, Hamed Bonab, Sheikh Muhammad Sarwar et al.

Pretrained contextualized representations offer great success for many downstream tasks, including document ranking. The multilingual versions of such pretrained representations provide a possibility of jointly learning many languages with the same model. Although it is expected to gain big with such joint training, in the case of cross lingual information retrieval (CLIR), the models under a multilingual setting are not achieving the same level of performance as those under a monolingual setting. We hypothesize that the performance drop is due to the translation gap between query and documents. In the monolingual retrieval task, because of the same lexical inputs, it is easier for model to identify the query terms that occurred in documents. However, in the multilingual pretrained models that the words in different languages are projected into the same hyperspace, the model tends to translate query terms into related terms, i.e., terms that appear in a similar context, in addition to or sometimes rather than synonyms in the target language. This property is creating difficulties for the model to connect terms that cooccur in both query and document. To address this issue, we propose a novel Mixed Attention Transformer (MAT) that incorporates external word level knowledge, such as a dictionary or translation table. We design a sandwich like architecture to embed MAT into the recent transformer based deep neural models. By encoding the translation knowledge into an attention matrix, the model with MAT is able to focus on the mutually translated words in the input sequence. Experimental results demonstrate the effectiveness of the external knowledge and the significant improvement of MAT embedded neural reranking model on CLIR task.

Shahrzad Naseri, Jeffrey Dalton, Andrew Yates et al.

In this work we leverage recent advances in context-sensitive language models to improve the task of query expansion. Contextualized word representation models, such as ELMo and BERT, are rapidly replacing static embedding models. We propose a new model, Contextualized Embeddings for Query Expansion (CEQE), that utilizes query-focused contextualized embedding vectors. We study the behavior of contextual representations generated for query expansion in ad-hoc document retrieval. We conduct our experiments on probabilistic retrieval models as well as in combination with neural ranking models. We evaluate CEQE on two standard TREC collections: Robust and Deep Learning. We find that CEQE outperforms static embedding-based expansion methods on multiple collections (by up to 18% on Robust and 31% on Deep Learning on average precision) and also improves over proven probabilistic pseudo-relevance feedback (PRF) models. We further find that multiple passes of expansion and reranking result in continued gains in effectiveness with CEQE-based approaches outperforming other approaches. The final model incorporating neural and CEQE-based expansion score achieves gains of up to 5% in P@20 and 2% in AP on Robust over the state-of-the-art transformer-based re-ranking model, Birch.

Puxuan Yu, James Allan

In this study, we investigate interaction-based neural matching models for ad-hoc cross-lingual information retrieval (CLIR) using cross-lingual word embeddings (CLWEs). With experiments conducted on the CLEF collection over four language pairs, we evaluate and provide insight into different neural model architectures, different ways to represent query-document interactions and word-pair similarity distributions in CLIR. This study paves the way for learning an end-to-end CLIR system using CLWEs.

Shahrzad Naseri, Sheikh Muhammad Sarwar, James Allan

A common approach for knowledge-base entity search is to consider an entity as a document with multiple fields. Models that focus on matching query terms in different fields are popular choices for searching such entity representations. An instance of such a model is FSDM (Fielded Sequential Dependence Model). We propose to integrate field-level semantic features into FSDM. We use FSDM to retrieve a pool of documents, and then to use semantic field-level features to re-rank those documents. We propose to represent queries as bags of terms as well as bags of entities, and eventually, use their dense vector representation to compute semantic features based on query document similarity. Our proposed re-ranking approach achieves significant improvement in entity retrieval on the DBpedia-Entity (v2) dataset over existing FSDM model. Specifically, for all queries we achieve 2.5% and 1.2% significant improvement in NDCG@10 and NDCG@100, respectively.

Sheikh Muhammad Sarwar, Hamed Bonab, James Allan

We describe a multi-task learning approach to train a Neural Machine Translation (NMT) model with a Relevance-based Auxiliary Task (RAT) for search query translation. The translation process for Cross-lingual Information Retrieval (CLIR) task is usually treated as a black box and it is performed as an independent step. However, an NMT model trained on sentence-level parallel data is not aware of the vocabulary distribution of the retrieval corpus. We address this problem with our multi-task learning architecture that achieves 16% improvement over a strong NMT baseline on Italian-English query-document dataset. We show using both quantitative and qualitative analysis that our model generates balanced and precise translations with the regularization effect it achieves from multi-task learning paradigm.

Myungha Jang, James Allan

In an era in which new controversies rapidly emerge and evolve on social media, navigating social media platforms to learn about a new controversy can be an overwhelming task. In this light, there has been significant work that studies how to identify and measure controversy online. However, we currently lack a tool for effectively understanding controversy in social media. For example, users have to manually examine postings to find the arguments of conflicting stances that make up the controversy. In this paper, we study methods to generate a stance-aware summary that explains a given controversy by collecting arguments of two conflicting stances. We focus on Twitter and treat stance summarization as a ranking problem of finding the top k tweets that best summarize the two conflicting stances of a controversial topic. We formalize the characteristics of a good stance summary and propose a ranking model accordingly. We first evaluate our methods on five controversial topics on Twitter. Our user evaluation shows that our methods consistently outperform other baseline techniques in generating a summary that explains the given controversy.

John Foley, Sheikh Muhammad Sarwar, James Allan

Traditional information retrieval treats named entity recognition as a pre-indexing corpus annotation task, allowing entity tags to be indexed and used during search. Named entity taggers themselves are typically trained on thousands or tens of thousands of examples labeled by humans. However, there is a long tail of named entities classes, and for these cases, labeled data may be impossible to find or justify financially. We propose exploring named entity recognition as a search task, where the named entity class of interest is a query, and entities of that class are the relevant "documents". What should that query look like? Can we even perform NER-style labeling with tens of labels? This study presents an exploration of CRF-based NER models with handcrafted features and of how we might transform them into search queries.

Sheikh Muhammad Sarwar, John Foley, James Allan

We address the role of a user in Contextual Named Entity Retrieval (CNER), showing (1) that user identification of important context-bearing terms is superior to automated approaches, and (2) that further gains are possible if the user indicates the relative importance of those terms. CNER is similar in spirit to List Question answering and Entity disambiguation. However, the main focus of CNER is to obtain user feedback for constructing a profile for a class of entities on the fly and use that to retrieve entities from free text. Given a sentence, and an entity selected from that sentence, CNER aims to retrieve sentences that have entities similar to query entity. This paper explores obtaining term relevance feedback and importance weighting from humans in order to improve a CNER system. We report our findings based on the efforts of IR researchers as well as crowdsourced workers.

Shiri Dori-Hacohen, Myungha Jang, James Allan

A growing body of research focuses on computationally detecting controversial topics and understanding the stances people hold on them. Yet gaps remain in our theoretical and practical understanding of how to define controversy, how it manifests, and how to measure it. In this paper, we introduce a novel measure we call "contention", defined with respect to a topic and a population. We model contention from a mathematical standpoint. We validate our model by examining a diverse set of sources: real-world polling data sets, actual voter data, and Twitter coverage on several topics. In our publicly-released Twitter data set of nearly 100M tweets, we examine several topics such as Brexit, the 2016 U.S. Elections, and "The Dress", and cross-reference them with other sources. We demonstrate that the contention measure holds explanatory power for a wide variety of observed phenomena, such as controversies over climate change and other topics that are well within scientific consensus. Finally, we re-examine the notion of controversy, and present a theoretical framework that defines it in terms of population. We present preliminary evidence suggesting that contention is one dimension of controversy, along with others, such as "importance". Our new contention measure, along with the hypothesized model of controversy, suggest several avenues for future work in this emerging interdisciplinary research area.

Myungha Jang, Jinho D. Choi, James Allan

Technical documents contain a fair amount of unnatural language, such as tables, formulas, pseudo-codes, etc. Unnatural language can be an important factor of confusing existing NLP tools. This paper presents an effective method of distinguishing unnatural language from natural language, and evaluates the impact of unnatural language detection on NLP tasks such as document clustering. We view this problem as an information extraction task and build a multiclass classification model identifying unnatural language components into four categories. First, we create a new annotated corpus by collecting slides and papers in various formats, PPT, PDF, and HTML, where unnatural language components are annotated into four categories. We then explore features available from plain text to build a statistical model that can handle any format as long as it is converted into plain text. Our experiments show that removing unnatural language components gives an absolute improvement in document clustering up to 15%. Our corpus and tool are publicly available.