Fernando Diaz

Alireza Salemi, Chang Zeng, Atharva Nijasure et al.

Large Language Model (LLM) search agents have shown strong promise for knowledge-intensive language tasks through multiple rounds of reasoning and information retrieval. Most existing systems access information using a retriever that takes a keyword or natural language query and returns a ranked list of documents using an index of pre-computed document representations. In this work, we explore a complementary perspective in which the search agent treats the corpus itself as the search environment and finds evidence by issuing executable shell commands. We introduce GrepSeek, an optimized direct corpus interaction (DCI) search agent that trains a compact search agent to find, filter, and compose evidence from large text corpora. To address the instability of learning behavior directly with reinforcement learning on large corpora, we propose a two-stage training pipeline. First, we construct a cold-start dataset using an answer-aware Tutor and answer-blind Planner to generate verified, causally grounded search trajectories. Second, we refine the initialized policy with Group Relative Policy Optimization (GRPO), allowing the agent to improve its task-oriented search behavior through direct interaction with the corpus. To make DCI practical at scale, we further use a semantics-preserving sharded-parallel execution engine that accelerates shell-based retrieval by up to $7.6\times$ while preserving byte-exact equivalence with sequential execution of the shell command. Experiments across seven open-domain question answering benchmarks show that GrepSeek achieves the strongest overall token-level $F_1$ and Exact Match. Our analysis also highlights the limitations of purely lexical interaction on queries with substantial surface-form variation, suggesting DCI as a practical and competitive method for search agents that can complement existing retrieval paradigms in the real world.

Haolun Wu, Bhaskar Mitra, Chen Ma et al. · microsoft-research

Prior research on exposure fairness in the context of recommender systems has focused mostly on disparities in the exposure of individual or groups of items to individual users of the system. The problem of how individual or groups of items may be systemically under or over exposed to groups of users, or even all users, has received relatively less attention. However, such systemic disparities in information exposure can result in observable social harms, such as withholding economic opportunities from historically marginalized groups (allocative harm) or amplifying gendered and racialized stereotypes (representational harm). Previously, Diaz et al. developed the expected exposure metric -- that incorporates existing user browsing models that have previously been developed for information retrieval -- to study fairness of content exposure to individual users. We extend their proposed framework to formalize a family of exposure fairness metrics that model the problem jointly from the perspective of both the consumers and producers. Specifically, we consider group attributes for both types of stakeholders to identify and mitigate fairness concerns that go beyond individual users and items towards more systemic biases in recommendation. Furthermore, we study and discuss the relationships between the different exposure fairness dimensions proposed in this paper, as well as demonstrate how stochastic ranking policies can be optimized towards said fairness goals.

Kai Hui, Tao Chen, Zhen Qin et al. · deepmind

Retrieval augmentation has shown promising improvements in different tasks. However, whether such augmentation can assist a large language model based re-ranker remains unclear. We investigate how to augment T5-based re-rankers using high-quality information retrieved from two external corpora -- a commercial web search engine and Wikipedia. We empirically demonstrate how retrieval augmentation can substantially improve the effectiveness of T5-based re-rankers for both in-domain and zero-shot out-of-domain re-ranking tasks.

Hamed Zamani, Fernando Diaz, Mostafa Dehghani et al.

Although information access systems have long supported people in accomplishing a wide range of tasks, we propose broadening the scope of users of information access systems to include task-driven machines, such as machine learning models. In this way, the core principles of indexing, representation, retrieval, and ranking can be applied and extended to substantially improve model generalization, scalability, robustness, and interpretability. We describe a generic retrieval-enhanced machine learning (REML) framework, which includes a number of existing models as special cases. REML challenges information retrieval conventions, presenting opportunities for novel advances in core areas, including optimization. The REML research agenda lays a foundation for a new style of information access research and paves a path towards advancing machine learning and artificial intelligence.

To Eun Kim, Alireza Salemi, Andrew Drozdov et al. · cmu

In the field of language modeling, models augmented with retrieval components have emerged as a promising solution to address several challenges faced in the natural language processing (NLP) field, including knowledge grounding, interpretability, and scalability. Despite the primary focus on NLP, we posit that the paradigm of retrieval-enhancement can be extended to a broader spectrum of machine learning (ML) such as computer vision, time series prediction, and computational biology. Therefore, this work introduces a formal framework of this paradigm, Retrieval-Enhanced Machine Learning (REML), by synthesizing the literature in various domains in ML with consistent notations which is missing from the current literature. Also, we found that while a number of studies employ retrieval components to augment their models, there is a lack of integration with foundational Information Retrieval (IR) research. We bridge this gap between the seminal IR research and contemporary REML studies by investigating each component that comprises the REML framework. Ultimately, the goal of this work is to equip researchers across various disciplines with a comprehensive, formally structured framework of retrieval-enhanced models, thereby fostering interdisciplinary future research.

To Eun Kim, Alireza Salemi, Hamed Zamani et al. · cmu

Modern information access ecosystems consist of mixtures of systems, such as retrieval systems and large language models, and increasingly rely on marketplaces to mediate access to models, tools, and data, making competition between systems inherent to deployment. In such settings, outcomes are shaped not only by benchmark quality but also by competitive pressure, including user switching, routing decisions, and operational constraints. Yet evaluation is still largely conducted on static benchmarks with accuracy-focused measures that assume systems operate in isolation. This mismatch makes it difficult to predict post-deployment success and obscures competitive effects such as early-adoption advantages and market dominance. We introduce Marketplace Evaluation, a simulation-based paradigm that evaluates information access systems as participants in a competitive marketplace. By simulating repeated interactions and evolving user and agent preferences, the framework enables longitudinal evaluation and marketplace-level metrics, such as retention and market share, that complement and can extend beyond traditional accuracy-based metrics. We formalize the framework and outline a research agenda, motivated by business and economics, around marketplace simulation, metrics, optimization, and adoption in evaluation campaigns like TREC.

To Eun Kim, Fernando Diaz · cmu

Despite the central role of retrieval in retrieval-augmented generation (RAG) systems, much of the existing research on RAG overlooks the well-established field of fair ranking and fails to account for the interests of all stakeholders involved. In this paper, we conduct the first systematic evaluation of RAG systems that integrate fairness-aware rankings, addressing both ranking fairness and attribution fairness, which ensures equitable exposure of the sources cited in the generated content. Our evaluation focuses on measuring item-side fairness, specifically the fair exposure of relevant items retrieved by RAG systems, and investigates how this fairness impacts both the effectiveness of the systems and the attribution of sources in the generated output that users ultimately see. By experimenting with twelve RAG models across seven distinct tasks, we show that incorporating fairness-aware retrieval often maintains or even enhances both ranking quality and generation quality, countering the common belief that fairness compromises system performance. Additionally, we demonstrate that fair retrieval practices lead to more balanced attribution in the final responses, ensuring that the generator fairly cites the sources it relies on. Our findings underscore the importance of item-side fairness in retrieval and generation, laying the foundation for responsible and equitable RAG systems and guiding future research in fair ranking and attribution.

Rebecca Salganik, Fernando Diaz, Golnoosh Farnadi

As online music platforms grow, music recommender systems play a vital role in helping users navigate and discover content within their vast musical databases. At odds with this larger goal, is the presence of popularity bias, which causes algorithmic systems to favor mainstream content over, potentially more relevant, but niche items. In this work we explore the intrinsic relationship between music discovery and popularity bias. To mitigate this issue we propose a domain-aware, individual fairness-based approach which addresses popularity bias in graph neural network (GNNs) based recommender systems. Our approach uses individual fairness to reflect a ground truth listening experience, i.e., if two songs sound similar, this similarity should be reflected in their representations. In doing so, we facilitate meaningful music discovery that is robust to popularity bias and grounded in the music domain. We apply our BOOST methodology to two discovery based tasks, performing recommendations at both the playlist level and user level. Then, we ground our evaluation in the cold start setting, showing that our approach outperforms existing fairness benchmarks in both performance and recommendation of lesser-known content. Finally, our analysis explains why our proposed methodology is a novel and promising approach to mitigating popularity bias and improving the discovery of new and niche content in music recommender systems.

Esther Rolf, Ben Packer, Alex Beutel et al.

Building trustworthy, effective, and responsible machine learning systems hinges on understanding how differences in training data and modeling decisions interact to impact predictive performance. In this work, we seek to better understand how we might characterize, detect, and design for data-model synergies. We focus on a particular type of data-model inefficiency, in which adding training data from some sources can actually lower performance evaluated on key sub-groups of the population, a phenomenon we refer to as negative data externalities on group performance. Such externalities can arise in standard learning settings and can manifest differently depending on conditions between training set size and model size. Data externalities directly imply a lower bound on feasible model improvements, yet improving models efficiently requires understanding the underlying data-model tensions. From a broader perspective, our results indicate that data-efficiency is a key component of both accurate and trustworthy machine learning.

Fernando Diaz, Michael Madaio

Recent work has advocated for training AI models on ever-larger datasets, arguing that as the size of a dataset increases, the performance of a model trained on that dataset will correspondingly increase (referred to as "scaling laws"). In this paper, we draw on literature from the social sciences and machine learning to critically interrogate these claims. We argue that this scaling law relationship depends on metrics used to measure performance that may not correspond with how different groups of people perceive the quality of models' output. As the size of datasets used to train large AI models grows and AI systems impact ever larger groups of people, the number of distinct communities represented in training or evaluation datasets grows. It is thus even more likely that communities represented in datasets may have values or preferences not reflected in (or at odds with) the metrics used to evaluate model performance in scaling laws. Different communities may also have values in tension with each other, leading to difficult, potentially irreconcilable choices about metrics used for model evaluations -- threatening the validity of claims that model performance is improving at scale. We end the paper with implications for AI development: that the motivation for scraping ever-larger datasets may be based on fundamentally flawed assumptions about model performance. That is, models may not, in fact, continue to improve as the datasets get larger -- at least not for all people or communities impacted by those models. We suggest opportunities for the field to rethink norms and values in AI development, resisting claims for universality of large models, fostering more local, small-scale designs, and other ways to resist the impetus towards scale in AI.

Rebecca Salganik, Fernando Diaz, Golnoosh Farnadi

Graph neural network (GNN) based methods have saturated the field of recommender systems. The gains of these systems have been significant, showing the advantages of interpreting data through a network structure. However, despite the noticeable benefits of using graph structures in recommendation tasks, this representational form has also bred new challenges which exacerbate the complexity of mitigating algorithmic bias. When GNNs are integrated into downstream tasks, such as recommendation, bias mitigation can become even more difficult. Furthermore, the intractability of applying existing methods of fairness promotion to large, real world datasets places even more serious constraints on mitigation attempts. Our work sets out to fill in this gap by taking an existing method for promoting individual fairness on graphs and extending it to support mini-batch, or sub-sample based, training of a GNN, thus laying the groundwork for applying this method to a downstream recommendation task. We evaluate two popular GNN methods: Graph Convolutional Network (GCN), which trains on the entire graph, and GraphSAGE, which uses probabilistic random walks to create subgraphs for mini-batch training, and assess the effects of sub-sampling on individual fairness. We implement an individual fairness notion called \textit{REDRESS}, proposed by Dong et al., which uses rank optimization to learn individual fair node, or item, embeddings. We empirically show on two real world datasets that GraphSAGE is able to achieve, not just, comparable accuracy, but also, improved fairness as compared with the GCN model. These finding have consequential ramifications to individual fairness promotion, GNNs, and in downstream form, recommender systems, showing that mini-batch training facilitate individual fairness promotion by allowing for local nuance to guide the process of fairness promotion in representation learning.

Xuhong He, To Eun Kim, Maik Fröbe et al.

Tip-of-the-Tongue (ToT) retrieval benchmarks have largely focused on English, limiting their applicability to multilingual information access. In this work, we construct multilingual ToT test collections for Chinese, Japanese, Korean, and English, using an LLM-based query simulation framework. We systematically study how prompt language and source document language affect the fidelity of simulated ToT queries, validating synthetic queries through system rank correlation against real user queries. Our results show that effective ToT simulation requires language-aware design choices: non-English language sources are generally important, while English Wikipedia can be beneficial when non-English sources provide insufficient information for query generation. Based on these findings, we release four ToT test collections with 5,000 queries per language across multiple domains. This work provides the first large-scale multilingual ToT benchmark and offers practical guidance for constructing realistic ToT datasets beyond English.

Jessica Huynh, Alfredo Gomez, Athiya Deviyani et al.

Autoraters, also referred to as LLM-as-judges, are increasingly used for evaluation and automated content moderation. However, there is limited statistical analysis of how modifications in a rubric presented to both humans and autoraters affect their score agreement. Rubrics that ask for an overall or \emph{holistic} judgment - for example, rating the ``quality'' of an essay - may be inconsistently interpreted due to the complexity or subjectivity of the criteria. Conversely, rubrics can ask for \emph{analytic} judgments, which decompose assessment criteria - for example, ``quality'' into ``fluency'' and ``organization''. While these rubrics can be edited to improve the individual accuracy of both human and automated scoring, this approach may result in disagreement between the two scores, or with the associated holistic judgment. Designing and deploying reliable autoraters requires understanding not just the relationship between human and autorater annotations but how that relationship changes as holistic or analytic judgments are elicited. The results indicate that rubric edits providing representative examples and additional context, and reducing positional bias in the rubric increased human-autorater agreement, while higher rubric complexity and conservative aggregation methods tended to decrease it. The findings from the automatic essay scoring and instruction-following evaluation domains suggest that practitioners should carefully analyze domain- and rubric-specific performance to move towards higher human-autorater agreement.

To Eun Kim, Fernando Diaz · cmu

Retrieval-Augmented Generation (RAG) systems typically rely on a single fixed retriever, despite growing evidence that no single retriever performs optimally across all query types. In this paper, we explore a query routing approach that dynamically selects from a pool of retrievers based on the query, using both train-free heuristics and learned routing models. We frame routing as a learning-to-rank (LTR) problem and introduce LTRR, a framework that learns to rank retrievers by their expected utility gain to downstream LLM performance. Our experiments, conducted on synthetic QA data with controlled query type variations, show that routing-based RAG systems can outperform the best single-retriever-based systems. Performance gains are especially pronounced in models trained with the Answer Correctness (AC) metric and with pairwise learning approaches, especially with XGBoost. We also observe improvements in generalization to out-of-distribution queries. As part of the SIGIR 2025 LiveRAG challenge, our submitted system demonstrated the practical viability of our approach, achieving competitive performance in both answer correctness and faithfulness. These findings highlight the importance of both training methodology and metric selection in query routing for RAG systems.

Alexandra Olteanu, Su Lin Blodgett, Agathe Balayn et al. · microsoft-research

In AI research and practice, rigor remains largely understood in terms of methodological rigor -- such as whether mathematical, statistical, or computational methods are correctly applied. We argue that this narrow conception of rigor has contributed to the concerns raised by the responsible AI community, including overblown claims about AI capabilities. Our position is that a broader conception of what rigorous AI research and practice should entail is needed. We believe such a conception -- in addition to a more expansive understanding of (1) methodological rigor -- should include aspects related to (2) what background knowledge informs what to work on (epistemic rigor); (3) how disciplinary, community, or personal norms, standards, or beliefs influence the work (normative rigor); (4) how clearly articulated the theoretical constructs under use are (conceptual rigor); (5) what is reported and how (reporting rigor); and (6) how well-supported the inferences from existing evidence are (interpretative rigor). In doing so, we also aim to provide useful language and a framework for much-needed dialogue about the AI community's work by researchers, policymakers, journalists, and other stakeholders.

Negar Arabzadeh, Fernando Diaz, Junfeng He

Text-to-Image (TTI) systems often support people during ideation, the early stages of a creative process when exposure to a broad set of relevant images can help explore the design space. Since ideation is an important subclass of TTI tasks, understanding how to quantitatively evaluate TTI systems according to how well they support ideation is crucial to promoting research and development for these users. However, existing evaluation metrics for TTI remain focused on distributional similarity metrics like Fréchet Inception Distance (FID). We take an alternative approach and, based on established methods from ranking evaluation, develop TTI evaluation metrics with explicit models of how users browse and interact with sets of spatially arranged generated images. Our proposed offline evaluation metrics for TTI not only capture how relevant generated images are with respect to the user's ideation need but also take into consideration the diversity and arrangement of the set of generated images. We analyze our proposed family of TTI metrics using human studies on image grids generated by three different TTI systems based on subsets of the widely used benchmarks such as MS-COCO captions and Localized Narratives as well as prompts used in naturalistic settings. Our results demonstrate that grounding metrics in how people use systems is an important and understudied area of benchmark design.

Yifan He, To Eun Kim, Fernando Diaz et al. · cmu

Tip-of-the-tongue (TOT) search occurs when a user struggles to recall a specific identifier, such as a document title. While common, existing search systems often fail to effectively support TOT scenarios. Research on TOT retrieval is further constrained by the challenge of collecting queries, as current approaches rely heavily on community question-answering (CQA) websites, leading to labor-intensive evaluation and domain bias. To overcome these limitations, we introduce two methods for eliciting TOT queries - leveraging large language models (LLMs) and human participants - to facilitate simulated evaluations of TOT retrieval systems. Our LLM-based TOT user simulator generates synthetic TOT queries at scale, achieving high correlations with how CQA-based TOT queries rank TOT retrieval systems when tested in the Movie domain. Additionally, these synthetic queries exhibit high linguistic similarity to CQA-derived queries. For human-elicited queries, we developed an interface that uses visual stimuli to place participants in a TOT state, enabling the collection of natural queries. In the Movie domain, system rank correlation and linguistic similarity analyses confirm that human-elicited queries are both effective and closely resemble CQA-based queries. These approaches reduce reliance on CQA-based data collection while expanding coverage to underrepresented domains, such as Landmark and Person. LLM-elicited queries for the Movie, Landmark, and Person domains have been released as test queries in the TREC 2024 TOT track, with human-elicited queries scheduled for inclusion in the TREC 2025 TOT track. Additionally, we provide source code for synthetic query generation and the human query collection interface, along with curated visual stimuli used for eliciting TOT queries.

Renee Shelby, Fernando Diaz, Vinodkumar Prabhakaran

The growing ubiquity of conversational AI highlights the need for frameworks that capture not only users' instrumental goals but also the situated, adaptive, and social practices through which they achieve them. Existing taxonomies of conversational behavior either overgeneralize, remain domain-specific, or reduce interactions to narrow dialogue functions. To address this gap, we introduce the Taxonomy of User Needs and Actions (TUNA), an empirically grounded framework developed through iterative qualitative analysis of 1193 human-AI conversations, supplemented by theoretical review and validation across diverse contexts. TUNA organizes user actions into a three-level hierarchy encompassing behaviors associated with information seeking, synthesis, procedural guidance, content creation, social interaction, and meta-conversation. By centering user agency and appropriation practices, TUNA enables multi-scale evaluation, supports policy harmonization across products, and provides a backbone for layering domain-specific taxonomies. This work contributes a systematic vocabulary for describing AI use, advancing both scholarly understanding and practical design of safer, more responsive, and more accountable conversational systems.

Abinay Reddy Naini, Fernando Diaz, Carlos Busso

Preference learning has gained significant attention in tasks involving subjective human judgments, such as \emph{speech emotion recognition} (SER) and image aesthetic assessment. While pairwise frameworks such as RankNet offer robust modeling of relative preferences, they are inherently limited to local comparisons and struggle to capture global ranking consistency. To address these limitations, we propose RankList, a novel listwise preference learning framework that generalizes RankNet to structured list-level supervision. Our formulation explicitly models local and non-local ranking constraints within a probabilistic framework. The paper introduces a log-sum-exp approximation to improve training efficiency. We further extend RankList with skip-wise comparisons, enabling progressive exposure to complex list structures and enhancing global ranking fidelity. Extensive experiments demonstrate the superiority of our method across diverse modalities. On benchmark SER datasets (MSP-Podcast, IEMOCAP, BIIC Podcast), RankList achieves consistent improvements in Kendall's Tau and ranking accuracy compared to standard listwise baselines. We also validate our approach on aesthetic image ranking using the Artistic Image Aesthetics dataset, highlighting its broad applicability. Through ablation and cross-domain studies, we show that RankList not only improves in-domain ranking but also generalizes better across datasets. Our framework offers a unified, extensible approach for modeling ordered preferences in subjective learning scenarios.

Jushaan Singh Kalra, Xinran Zhao, To Eun Kim et al. · cmu

Retrieval-augmented Generation (RAG) is powerful, but its effectiveness hinges on which retrievers we use and how. Different retrievers offer distinct, often complementary signals: BM25 captures lexical matches; dense retrievers, semantic similarity. Yet in practice, we typically fix a single retriever based on heuristics, which fails to generalize across diverse information needs. Can we dynamically select and integrate multiple retrievers for each individual query, without the need for manual selection? In our work, we validate this intuition with quantitative analysis and introduce mixture of retrievers: a zero-shot, weighted combination of heterogeneous retrievers. Extensive experiments show that such mixtures are effective and efficient: Despite totaling just 0.8B parameters, this mixture outperforms every individual retriever and even larger 7B models by +10.8% and +3.9% on average, respectively. Further analysis also shows that this mixture framework can help incorporate specialized non-oracle human information sources as retrievers to achieve good collaboration, with a 58.9% relative performance improvement over simulated humans alone.

Athiya Deviyani, Fernando Diaz

Meta-evaluation of automatic evaluation metrics -- assessing evaluation metrics themselves -- is crucial for accurately benchmarking natural language processing systems and has implications for scientific inquiry, production model development, and policy enforcement. While existing approaches to metric meta-evaluation focus on general statements about the absolute and relative quality of metrics across arbitrary system outputs, in practice, metrics are applied in highly contextual settings, often measuring the performance for a highly constrained set of system outputs. For example, we may only be interested in evaluating a specific model or class of models. We introduce a method for contextual metric meta-evaluation by comparing the local metric accuracy of evaluation metrics. Across translation, speech recognition, and ranking tasks, we demonstrate that the local metric accuracies vary both in absolute value and relative effectiveness as we shift across evaluation contexts. This observed variation highlights the importance of adopting context-specific metric evaluations over global ones.

Shaily Bhatt, Fernando Diaz

Productive interactions between diverse users and language technologies require outputs from the latter to be culturally relevant and sensitive. Prior works have evaluated models' knowledge of cultural norms, values, and artifacts, without considering how this knowledge manifests in downstream applications. In this work, we focus on extrinsic evaluation of cultural competence in two text generation tasks, open-ended question answering and story generation. We quantitatively and qualitatively evaluate model outputs when an explicit cue of culture, specifically nationality, is perturbed in the prompts. Although we find that model outputs do vary when varying nationalities and feature culturally relevant words, we also find weak correlations between text similarity of outputs for different countries and the cultural values of these countries. Finally, we discuss important considerations in designing comprehensive evaluation of cultural competence in user-facing tasks.

Ruohan Li, Jianxiang Li, Bhaskar Mitra et al.

Search systems control the exposure of ranked content to searchers. In many cases, creators value not only the exposure of their content but, moreover, an understanding of the specific searches where the content is surfaced. The problem of identifying which queries expose a given piece of content in the ranking results is an important and relatively under-explored search transparency challenge. Exposing queries are useful for quantifying various issues of search bias, privacy, data protection, security, and search engine optimization. Exact identification of exposing queries in a given system is computationally expensive, especially in dynamic contexts such as web search. We explore the feasibility of approximate exposing query identification (EQI) as a retrieval task by reversing the role of queries and documents in two classes of search systems: dense dual-encoder models and traditional BM25 models. We then propose how this approach can be improved through metric learning over the retrieval embedding space. We further derive an evaluation metric to measure the quality of a ranking of exposing queries, as well as conducting an empirical analysis focusing on various practical aspects of approximate EQI. Overall, our work contributes a novel conception of transparency in search systems and computational means of achieving it.

Ömer Kırnap, Fernando Diaz, Asia Biega et al.

There is increasing attention to evaluating the fairness of search system ranking decisions. These metrics often consider the membership of items to particular groups, often identified using protected attributes such as gender or ethnicity. To date, these metrics typically assume the availability and completeness of protected attribute labels of items. However, the protected attributes of individuals are rarely present, limiting the application of fair ranking metrics in large scale systems. In order to address this problem, we propose a sampling strategy and estimation technique for four fair ranking metrics. We formulate a robust and unbiased estimator which can operate even with very limited number of labeled items. We evaluate our approach using both simulated and real world data. Our experimental results demonstrate that our method can estimate this family of fair ranking metrics and provides a robust, reliable alternative to exhaustive or random data annotation.

Asia J. Biega, Fernando Diaz, Michael D. Ekstrand et al.

This paper provides an overview of the NIST TREC 2020 Fair Ranking track. For 2020, we again adopted an academic search task, where we have a corpus of academic article abstracts and queries submitted to a production academic search engine. The central goal of the Fair Ranking track is to provide fair exposure to different groups of authors (a group fairness framing). We recognize that there may be multiple group definitions (e.g. based on demographics, stature, topic) and hoped for the systems to be robust to these. We expected participants to develop systems that optimize for fairness and relevance for arbitrary group definitions, and did not reveal the exact group definitions until after the evaluation runs were submitted.The track contains two tasks,reranking and retrieval, with a shared evaluation.

Divya Shanmugam, Samira Shabanian, Fernando Diaz et al.

Modern machine learning systems are increasingly characterized by extensive personal data collection, despite the diminishing returns and increasing societal costs of such practices. Yet, data minimisation is one of the core data protection principles enshrined in the European Union's General Data Protection Regulation ('GDPR') and requires that only personal data that is adequate, relevant and limited to what is necessary is processed. However, the principle has seen limited adoption due to the lack of technical interpretation. In this work, we build on literature in machine learning and law to propose FIDO, a Framework for Inhibiting Data Overcollection. FIDO learns to limit data collection based on an interpretation of data minimization tied to system performance. Concretely, FIDO provides a data collection stopping criterion by iteratively updating an estimate of the performance curve, or the relationship between dataset size and performance, as data is acquired. FIDO estimates the performance curve via a piecewise power law technique that models distinct phases of an algorithm's performance throughout data collection separately. Empirical experiments show that the framework produces accurate performance curves and data collection stopping criteria across datasets and feature acquisition algorithms. We further demonstrate that many other families of curves systematically overestimate the return on additional data. Results and analysis from our investigation offer deeper insights into the relevant considerations when designing a data minimization framework, including the impacts of active feature acquisition on individual users and the feasability of user-specific data minimization. We conclude with practical recommendations for the implementation of data minimization.

Mostafa Dehghani, Yi Tay, Alexey A. Gritsenko et al.

The world of empirical machine learning (ML) strongly relies on benchmarks in order to determine the relative effectiveness of different algorithms and methods. This paper proposes the notion of "a benchmark lottery" that describes the overall fragility of the ML benchmarking process. The benchmark lottery postulates that many factors, other than fundamental algorithmic superiority, may lead to a method being perceived as superior. On multiple benchmark setups that are prevalent in the ML community, we show that the relative performance of algorithms may be altered significantly simply by choosing different benchmark tasks, highlighting the fragility of the current paradigms and potential fallacious interpretation derived from benchmarking ML methods. Given that every benchmark makes a statement about what it perceives to be important, we argue that this might lead to biased progress in the community. We discuss the implications of the observed phenomena and provide recommendations on mitigating them using multiple machine learning domains and communities as use cases, including natural language processing, computer vision, information retrieval, recommender systems, and reinforcement learning.

Michael D. Ekstrand, Anubrata Das, Robin Burke et al.

Recommendation, information retrieval, and other information access systems pose unique challenges for investigating and applying the fairness and non-discrimination concepts that have been developed for studying other machine learning systems. While fair information access shares many commonalities with fair classification, the multistakeholder nature of information access applications, the rank-based problem setting, the centrality of personalization in many cases, and the role of user response complicate the problem of identifying precisely what types and operationalizations of fairness may be relevant, let alone measuring or promoting them. In this monograph, we present a taxonomy of the various dimensions of fair information access and survey the literature to date on this new and rapidly-growing topic. We preface this with brief introductions to information access and algorithmic fairness, to facilitate use of this work by scholars with experience in one (or neither) of these fields who wish to learn about their intersection. We conclude with several open problems in fair information access, along with some suggestions for how to approach research in this space.

Haolun Wu, Chen Ma, Bhaskar Mitra et al.

Nowadays, most online services are hosted on multi-stakeholder marketplaces, where consumers and producers may have different objectives. Conventional recommendation systems, however, mainly focus on maximizing consumers' satisfaction by recommending the most relevant items to each individual. This may result in unfair exposure of items, thus jeopardizing producer benefits. Additionally, they do not care whether consumers from diverse demographic groups are equally satisfied. To address these limitations, we propose a multi-objective optimization framework for fairness-aware recommendation, Multi-FR, that adaptively balances accuracy and fairness for various stakeholders with Pareto optimality guarantee. We first propose four fairness constraints on consumers and producers. In order to train the whole framework in an end-to-end way, we utilize the smooth rank and stochastic ranking policy to make these fairness criteria differentiable and friendly to back-propagation. Then, we adopt the multiple gradient descent algorithm to generate a Pareto set of solutions, from which the most appropriate one is selected by the Least Misery Strategy. The experimental results demonstrate that Multi-FR largely improves recommendation fairness on multiple stakeholders over the state-of-the-art approaches while maintaining almost the same recommendation accuracy. The training efficiency study confirms our model's ability to simultaneously optimize different fairness constraints for many stakeholders efficiently.

Jaime Arguello, Adam Ferguson, Emery Fine et al.

While current information retrieval systems are effective for known-item retrieval where the searcher provides a precise name or identifier for the item being sought, systems tend to be much less effective for cases where the searcher is unable to express a precise name or identifier. We refer to this as tip of the tongue (TOT) known-item retrieval, named after the cognitive state of not being able to retrieve an item from memory. Using movie search as a case study, we explore the characteristics of questions posed by searchers in TOT states in a community question answering website. We analyze how searchers express their information needs during TOT states in the movie domain. Specifically, what information do searchers remember about the item being sought and how do they convey this information? Our results suggest that searchers use a combination of information about: (1) the content of the item sought, (2) the context in which they previously engaged with the item, and (3) previous attempts to find the item using other resources (e.g., search engines). Additionally, searchers convey information by sometimes expressing uncertainty (i.e., hedging), opinions, emotions, and by performing relative (vs. absolute) comparisons with attributes of the item. As a result of our analysis, we believe that searchers in TOT states may require specialized query understanding methods or document representations. Finally, our preliminary retrieval experiments show the impact of each information type presented in information requests on retrieval performance.

Timothy J. Hazen, Alexandra Olteanu, Gabriella Kazai et al.

Past research shows that users benefit from systems that support them in their writing and exploration tasks. The autosuggestion feature of Web search engines is an example of such a system: It helps users in formulating their queries by offering a list of suggestions as they type. Autosuggestions are typically generated by machine learning (ML) systems trained on a corpus of search logs and document representations. Such automated methods can become prone to issues that result in problematic suggestions that are biased, racist, sexist or in other ways inappropriate. While current search engines have become increasingly proficient at suppressing such problematic suggestions, there are still persistent issues that remain. In this paper, we reflect on past efforts and on why certain issues still linger by covering explored solutions along a prototypical pipeline for identifying, detecting, and addressing problematic autosuggestions. To showcase their complexity, we discuss several dimensions of problematic suggestions, difficult issues along the pipeline, and why our discussion applies to the increasing number of applications beyond web search that implement similar textual suggestion features. By outlining persistent social and technical challenges in moderating web search suggestions, we provide a renewed call for action.

Hamed Zamani, Bhaskar Mitra, Everest Chen et al.

Asking clarifying questions in response to search queries has been recognized as a useful technique for revealing the underlying intent of the query. Clarification has applications in retrieval systems with different interfaces, from the traditional web search interfaces to the limited bandwidth interfaces as in speech-only and small screen devices. Generation and evaluation of clarifying questions have been recently studied in the literature. However, user interaction with clarifying questions is relatively unexplored. In this paper, we conduct a comprehensive study by analyzing large-scale user interactions with clarifying questions in a major web search engine. In more detail, we analyze the user engagements received by clarifying questions based on different properties of search queries, clarifying questions, and their candidate answers. We further study click bias in the data, and show that even though reading clarifying questions and candidate answers does not take significant efforts, there still exist some position and presentation biases in the data. We also propose a model for learning representation for clarifying questions based on the user interaction data as implicit feedback. The model is used for re-ranking a number of automatically generated clarifying questions for a given query. Evaluation on both click data and human labeled data demonstrates the high quality of the proposed method.

Asia J. Biega, Peter Potash, Hal Daumé et al.

Article 5(1)(c) of the European Union's General Data Protection Regulation (GDPR) requires that "personal data shall be [...] adequate, relevant, and limited to what is necessary in relation to the purposes for which they are processed (`data minimisation')". To date, the legal and computational definitions of `purpose limitation' and `data minimization' remain largely unclear. In particular, the interpretation of these principles is an open issue for information access systems that optimize for user experience through personalization and do not strictly require personal data collection for the delivery of basic service. In this paper, we identify a lack of a homogeneous interpretation of the data minimization principle and explore two operational definitions applicable in the context of personalization. The focus of our empirical study in the domain of recommender systems is on providing foundational insights about the (i) feasibility of different data minimization definitions, (ii) robustness of different recommendation algorithms to minimization, and (iii) performance of different minimization strategies.We find that the performance decrease incurred by data minimization might not be substantial, but that it might disparately impact different users---a finding which has implications for the viability of different formal minimization definitions. Overall, our analysis uncovers the complexities of the data minimization problem in the context of personalization and maps the remaining computational and regulatory challenges.

Fernando Diaz, Bhaskar Mitra, Michael D. Ekstrand et al.

We introduce the concept of \emph{expected exposure} as the average attention ranked items receive from users over repeated samples of the same query. Furthermore, we advocate for the adoption of the principle of equal expected exposure: given a fixed information need, no item should receive more or less expected exposure than any other item of the same relevance grade. We argue that this principle is desirable for many retrieval objectives and scenarios, including topical diversity and fair ranking. Leveraging user models from existing retrieval metrics, we propose a general evaluation methodology based on expected exposure and draw connections to related metrics in information retrieval evaluation. Importantly, this methodology relaxes classic information retrieval assumptions, allowing a system, in response to a query, to produce a \emph{distribution over rankings} instead of a single fixed ranking. We study the behavior of the expected exposure metric and stochastic rankers across a variety of information access conditions, including \emph{ad hoc} retrieval and recommendation. We believe that measuring and optimizing expected exposure metrics using randomization opens a new area for retrieval algorithm development and progress.

Asia J. Biega, Fernando Diaz, Michael D. Ekstrand et al.

The goal of the TREC Fair Ranking track was to develop a benchmark for evaluating retrieval systems in terms of fairness to different content providers in addition to classic notions of relevance. As part of the benchmark, we defined standardized fairness metrics with evaluation protocols and released a dataset for the fair ranking problem. The 2019 task focused on reranking academic paper abstracts given a query. The objective was to fairly represent relevant authors from several groups that were unknown at the system submission time. Thus, the track emphasized the development of systems which have robust performance across a variety of group definitions. Participants were provided with querylog data (queries, documents, and relevance) from Semantic Scholar. This paper presents an overview of the track, including the task definition, descriptions of the data and the annotation process, as well as a comparison of the performance of submitted systems.

Bhaskar Mitra, Corby Rosset, David Hawking et al.

Classical information retrieval (IR) methods, such as query likelihood and BM25, score documents independently w.r.t. each query term, and then accumulate the scores. Assuming query term independence allows precomputing term-document scores using these models---which can be combined with specialized data structures, such as inverted index, for efficient retrieval. Deep neural IR models, in contrast, compare the whole query to the document and are, therefore, typically employed only for late stage re-ranking. We incorporate query term independence assumption into three state-of-the-art neural IR models: BERT, Duet, and CKNRM---and evaluate their performance on a passage ranking task. Surprisingly, we observe no significant loss in result quality for Duet and CKNRM---and a small degradation in the case of BERT. However, by operating on each query term independently, these otherwise computationally intensive models become amenable to offline precomputation---dramatically reducing the cost of query evaluations employing state-of-the-art neural ranking models. This strategy makes it practical to use deep models for retrieval from large collections---and not restrict their usage to late stage re-ranking.

Rishabh Mehrotra, Ashton Anderson, Fernando Diaz et al.

Many online services, such as search engines, social media platforms, and digital marketplaces, are advertised as being available to any user, regardless of their age, gender, or other demographic factors. However, there are growing concerns that these services may systematically underserve some groups of users. In this paper, we present a framework for internally auditing such services for differences in user satisfaction across demographic groups, using search engines as a case study. We first explain the pitfalls of naïvely comparing the behavioral metrics that are commonly used to evaluate search engines. We then propose three methods for measuring latent differences in user satisfaction from observed differences in evaluation metrics. To develop these methods, we drew on ideas from the causal inference literature and the multilevel modeling literature. Our framework is broadly applicable to other online services, and provides general insight into interpreting their evaluation metrics.

Bhaskar Mitra, Fernando Diaz, Nick Craswell

In recent years, the information retrieval (IR) community has witnessed the first successful applications of deep neural network models to short-text matching and ad-hoc retrieval. It is exciting to see the research on deep neural networks and IR converge on these tasks of shared interest. However, the two communities have less in common when it comes to the choice of programming languages. Indri, an indexing framework popularly used by the IR community, is written in C++, while Torch, a popular machine learning library for deep learning, is written in the light-weight scripting language Lua. To bridge this gap, we introduce Luandri (pronounced "laundry"), a simple interface for exposing the search capabilities of Indri to Torch models implemented in Lua.

Bhaskar Mitra, Fernando Diaz, Nick Craswell

Models such as latent semantic analysis and those based on neural embeddings learn distributed representations of text, and match the query against the document in the latent semantic space. In traditional information retrieval models, on the other hand, terms have discrete or local representations, and the relevance of a document is determined by the exact matches of query terms in the body text. We hypothesize that matching with distributed representations complements matching with traditional local representations, and that a combination of the two is favorable. We propose a novel document ranking model composed of two separate deep neural networks, one that matches the query and the document using a local representation, and another that matches the query and the document using learned distributed representations. The two networks are jointly trained as part of a single neural network. We show that this combination or `duet' performs significantly better than either neural network individually on a Web page ranking task, and also significantly outperforms traditional baselines and other recently proposed models based on neural networks.

Rahul Goel, Sandeep Soni, Naman Goyal et al.

Language change is a complex social phenomenon, revealing pathways of communication and sociocultural influence. But, while language change has long been a topic of study in sociolinguistics, traditional linguistic research methods rely on circumstantial evidence, estimating the direction of change from differences between older and younger speakers. In this paper, we use a data set of several million Twitter users to track language changes in progress. First, we show that language change can be viewed as a form of social influence: we observe complex contagion for phonetic spellings and "netspeak" abbreviations (e.g., lol), but not for older dialect markers from spoken language. Next, we test whether specific types of social network connections are more influential than others, using a parametric Hawkes process model. We find that tie strength plays an important role: densely embedded social ties are significantly better conduits of linguistic influence. Geographic locality appears to play a more limited role: we find relatively little evidence to support the hypothesis that individuals are more influenced by geographically local social ties, even in their usage of geographical dialect markers.

Fernando Diaz, Bhaskar Mitra, Nick Craswell

Continuous space word embeddings have received a great deal of attention in the natural language processing and machine learning communities for their ability to model term similarity and other relationships. We study the use of term relatedness in the context of query expansion for ad hoc information retrieval. We demonstrate that word embeddings such as word2vec and GloVe, when trained globally, underperform corpus and query specific embeddings for retrieval tasks. These results suggest that other tasks benefiting from global embeddings may also benefit from local embeddings.

Chris Kedzie, Fernando Diaz, Kathleen McKeown

We present a system based on sequential decision making for the online summarization of massive document streams, such as those found on the web. Given an event of interest (e.g. "Boston marathon bombing"), our system is able to filter the stream for relevance and produce a series of short text updates describing the event as it unfolds over time. Unlike previous work, our approach is able to jointly model the relevance, comprehensiveness, novelty, and timeliness required by time-sensitive queries. We demonstrate a 28.3% improvement in summary F1 and a 43.8% improvement in time-sensitive F1 metrics.

Eneko Osaba, Xin-She Yang, Fernando Diaz et al.

Bat algorithm is a population metaheuristic proposed in 2010 which is based on the echolocation or bio-sonar characteristics of microbats. Since its first implementation, the bat algorithm has been used in a wide range of fields. In this paper, we present a discrete version of the bat algorithm to solve the well-known symmetric and asymmetric traveling salesman problems. In addition, we propose an improvement in the basic structure of the classic bat algorithm. To prove that our proposal is a promising approximation method, we have compared its performance in 37 instances with the results obtained by five different techniques: evolutionary simulated annealing, genetic algorithm, an island based distributed genetic algorithm, a discrete firefly algorithm and an imperialist competitive algorithm. In order to obtain fair and rigorous comparisons, we have conducted three different statistical tests along the paper: the Student's $t$-test, the Holm's test, and the Friedman test. We have also compared the convergence behaviour shown by our proposal with the ones shown by the evolutionary simulated annealing, and the discrete firefly algorithm. The experimentation carried out in this study has shown that the presented improved bat algorithm outperforms significantly all the other alternatives in most of the cases.

David Abel, Alekh Agarwal, Fernando Diaz et al.

High-dimensional observations and complex real-world dynamics present major challenges in reinforcement learning for both function approximation and exploration. We address both of these challenges with two complementary techniques: First, we develop a gradient-boosting style, non-parametric function approximator for learning on $Q$-function residuals. And second, we propose an exploration strategy inspired by the principles of state abstraction and information acquisition under uncertainty. We demonstrate the empirical effectiveness of these techniques, first, as a preliminary check, on two standard tasks (Blackjack and $n$-Chain), and then on two much larger and more realistic tasks with high-dimensional observation spaces. Specifically, we introduce two benchmarks built within the game Minecraft where the observations are pixel arrays of the agent's visual field. A combination of our two algorithmic techniques performs competitively on the standard reinforcement-learning tasks while consistently and substantially outperforming baselines on the two tasks with high-dimensional observation spaces. The new function approximator, exploration strategy, and evaluation benchmarks are each of independent interest in the pursuit of reinforcement-learning methods that scale to real-world domains.

Fernando Diaz

Automatic query reformulation refers to rewriting a user's original query in order to improve the ranking of retrieval results compared to the original query. We present a general framework for automatic query reformulation based on discrete optimization. Our approach, referred to as pseudo-query reformulation, treats automatic query reformulation as a search problem over the graph of unweighted queries linked by minimal transformations (e.g. term additions, deletions). This framework allows us to test existing performance prediction methods as heuristics for the graph search process. We demonstrate the effectiveness of the approach on several publicly available datasets.