On the Scaling of Robustness and Effectiveness in Dense Retrieval

Robustness and Effectiveness are critical aspects of developing dense retrieval models for real-world applications. It is known that there is a trade-off between the two. Recent work has addressed scaling laws of effectiveness in dense retrieval, revealing a power-law relationship between effectiveness and the size of models and data. Does robustness follow scaling laws too? If so, can scaling improve both robustness and effectiveness together, or do they remain locked in a trade-off? To answer these questions, we conduct a comprehensive experimental study. We find that:(i) Robustness, including out-of-distribution and adversarial robustness, also follows a scaling law.(ii) Robustness and effectiveness exhibit different scaling patterns, leading to significant resource costs when jointly improving both. Given these findings, we shift to the third factor that affects model performance, namely the optimization strategy, beyond the model size and data size. We find that: (i) By fitting different optimization strategies, the joint performance of robustness and effectiveness traces out a Pareto frontier. (ii) When the optimization strategy strays from Pareto efficiency, the joint performance scales in a sub-optimal direction. (iii) By adjusting the optimization weights to fit the Pareto efficiency, we can achieve Pareto training, where the scaling of joint performance becomes most efficient. Even without requiring additional resources, Pareto training is comparable to the performance of scaling resources several times under optimization strategies that overly prioritize either robustness or effectiveness. Finally, we demonstrate that our findings can help deploy dense retrieval models in real-world applications that scale efficiently and are balanced for robustness and effectiveness.

Iterative Self-Incentivization Empowers Large Language Models as Agentic Searchers

Large language models (LLMs) have been widely integrated into information retrieval to advance traditional techniques. However, effectively enabling LLMs to seek accurate knowledge in complex tasks remains a challenge due to the complexity of multi-hop queries as well as the irrelevant retrieved content. To address these limitations, we propose EXSEARCH, an agentic search framework, where the LLM learns to retrieve useful information as the reasoning unfolds through a self-incentivized process. At each step, the LLM decides what to retrieve (thinking), triggers an external retriever (search), and extracts fine-grained evidence (recording) to support next-step reasoning. To enable LLM with this capability, EXSEARCH adopts a Generalized Expectation-Maximization algorithm. In the E-step, the LLM generates multiple search trajectories and assigns an importance weight to each; the M-step trains the LLM on them with a re-weighted loss function. This creates a self-incentivized loop, where the LLM iteratively learns from its own generated data, progressively improving itself for search. We further theoretically analyze this training process, establishing convergence guarantees. Extensive experiments on four knowledge-intensive benchmarks show that EXSEARCH substantially outperforms baselines, e.g., +7.8% improvement on exact match score. Motivated by these promising results, we introduce EXSEARCH-Zoo, an extension that extends our method to broader scenarios, to facilitate future work.

Optimized Text Embedding Models and Benchmarks for Amharic Passage Retrieval

Neural retrieval methods using transformer-based pre-trained language models have advanced multilingual and cross-lingual retrieval. However, their effectiveness for low-resource, morphologically rich languages such as Amharic remains underexplored due to data scarcity and suboptimal tokenization. We address this gap by introducing Amharic-specific dense retrieval models based on pre-trained Amharic BERT and RoBERTa backbones. Our proposed RoBERTa-Base-Amharic-Embed model (110M parameters) achieves a 17.6% relative improvement in MRR@10 and a 9.86% gain in Recall@10 over the strongest multilingual baseline, Arctic Embed 2.0 (568M parameters). More compact variants, such as RoBERTa-Medium-Amharic-Embed (42M), remain competitive while being over 13x smaller. Additionally, we train a ColBERT-based late interaction retrieval model that achieves the highest MRR@10 score (0.843) among all evaluated models. We benchmark our proposed models against both sparse and dense retrieval baselines to systematically assess retrieval effectiveness in Amharic. Our analysis highlights key challenges in low-resource settings and underscores the importance of language-specific adaptation. To foster future research in low-resource IR, we publicly release our dataset, codebase, and trained models at https://github.com/kidist-amde/amharic-ir-benchmarks.

The Silent Saboteur: Imperceptible Adversarial Attacks against Black-Box Retrieval-Augmented Generation Systems

We explore adversarial attacks against retrieval-augmented generation (RAG) systems to identify their vulnerabilities. We focus on generating human-imperceptible adversarial examples and introduce a novel imperceptible retrieve-to-generate attack against RAG. This task aims to find imperceptible perturbations that retrieve a target document, originally excluded from the initial top-$k$ candidate set, in order to influence the final answer generation. To address this task, we propose ReGENT, a reinforcement learning-based framework that tracks interactions between the attacker and the target RAG and continuously refines attack strategies based on relevance-generation-naturalness rewards. Experiments on newly constructed factual and non-factual question-answering benchmarks demonstrate that ReGENT significantly outperforms existing attack methods in misleading RAG systems with small imperceptible text perturbations.

Direct Retrieval-augmented Optimization: Synergizing Knowledge Selection and Language Models

Retrieval-augmented generation (RAG) integrates large language models ( LLM s) with retrievers to access external knowledge, improving the factuality of LLM generation in knowledge-grounded tasks. To optimize the RAG performance, most previous work independently fine-tunes the retriever to adapt to frozen LLM s or trains the LLMs to use documents retrieved by off-the-shelf retrievers, lacking end-to-end training supervision. Recent work addresses this limitation by jointly training these two components but relies on overly simplifying assumptions of document independence, which has been criticized for being far from real-world scenarios. Thus, effectively optimizing the overall RAG performance remains a critical challenge. We propose a direct retrieval-augmented optimization framework, named DRO, that enables end-to-end training of two key components: (i) a generative knowledge selection model and (ii) an LLM generator. DRO alternates between two phases: (i) document permutation estimation and (ii) re-weighted maximization, progressively improving RAG components through a variational approach. In the estimation step, we treat document permutation as a latent variable and directly estimate its distribution from the selection model by applying an importance sampling strategy. In the maximization step, we calibrate the optimization expectation using importance weights and jointly train the selection model and LLM generator. Our theoretical analysis reveals that DRO is analogous to policy-gradient methods in reinforcement learning. Extensive experiments conducted on five datasets illustrate that DRO outperforms the best baseline with 5%-15% improvements in EM and F1. We also provide in-depth experiments to qualitatively analyze the stability, convergence, and variance of DRO.

RecGaze: The First Eye Tracking and User Interaction Dataset for Carousel Interfaces

Carousel interfaces are widely used in e-commerce and streaming services, but little research has been devoted to them. Previous studies of interfaces for presenting search and recommendation results have focused on single ranked lists, but it appears their results cannot be extrapolated to carousels due to the added complexity. Eye tracking is a highly informative approach to understanding how users click, yet there are no eye tracking studies concerning carousels. There are very few interaction datasets on recommenders with carousel interfaces and none that contain gaze data. We introduce the RecGaze dataset: the first comprehensive feedback dataset on carousels that includes eye tracking results, clicks, cursor movements, and selection explanations. The dataset comprises of interactions from 3 movie selection tasks with 40 different carousel interfaces per user. In total, 87 users and 3,477 interactions are logged. In addition to the dataset, its description and possible use cases, we provide results of a survey on carousel design and the first analysis of gaze data on carousels, which reveals a golden triangle or F-pattern browsing behavior. Our work seeks to advance the field of carousel interfaces by providing the first dataset with eye tracking results on carousels. In this manner, we provide and encourage an empirical understanding of interactions with carousel interfaces, for building better recommender systems through gaze information, and also encourage the development of gaze-based recommenders.

An Empirical Study of Evaluating Long-form Question Answering

\Ac{LFQA} aims to generate lengthy answers to complex questions. This scenario presents great flexibility as well as significant challenges for evaluation. Most evaluations rely on deterministic metrics that depend on string or n-gram matching, while the reliability of large language model-based evaluations for long-form answers remains relatively unexplored. We address this gap by conducting an in-depth study of long-form answer evaluation with the following research questions: (i) To what extent do existing automatic evaluation metrics serve as a substitute for human evaluations? (ii) What are the limitations of existing evaluation metrics compared to human evaluations? (iii) How can the effectiveness and robustness of existing evaluation methods be improved? We collect 5,236 factoid and non-factoid long-form answers generated by different large language models and conduct a human evaluation on 2,079 of them, focusing on correctness and informativeness. Subsequently, we investigated the performance of automatic evaluation metrics by evaluating these answers, analyzing the consistency between these metrics and human evaluations. We find that the style, length of the answers, and the category of questions can bias the automatic evaluation metrics. However, fine-grained evaluation helps mitigate this issue on some metrics. Our findings have important implications for the use of large language models for evaluating long-form question answering. All code and datasets are available at https://github.com/bugtig6351/lfqa_evaluation.

Replication and Exploration of Generative Retrieval over Dynamic Corpora

Generative retrieval (GR) has emerged as a promising paradigm in information retrieval (IR). However, most existing GR models are developed and evaluated using a static document collection, and their performance in dynamic corpora where document collections evolve continuously is rarely studied. In this paper, we first reproduce and systematically evaluate various representative GR approaches over dynamic corpora. Through extensive experiments, we reveal that existing GR models with \textit{text-based} docids show superior generalization to unseen documents. We observe that the more fine-grained the docid design in the GR model, the better its performance over dynamic corpora, surpassing BM25 and even being comparable to dense retrieval methods. While GR models with \textit{numeric-based} docids show high efficiency, their performance drops significantly over dynamic corpora. Furthermore, our experiments find that the underperformance of numeric-based docids is partly due to their excessive tendency toward the initial document set, which likely results from overfitting on the training set. We then conduct an in-depth analysis of the best-performing GR methods. We identify three critical advantages of text-based docids in dynamic corpora: (i) Semantic alignment with language models' pretrained knowledge, (ii) Fine-grained docid design, and (iii) High lexical diversity. Building on these insights, we finally propose a novel multi-docid design that leverages both the efficiency of numeric-based docids and the effectiveness of text-based docids, achieving improved performance in dynamic corpus without requiring additional retraining. Our work offers empirical evidence for advancing GR methods over dynamic corpora and paves the way for developing more generalized yet efficient GR models in real-world search engines.

Adaptive Orchestration of Modular Generative Information Access Systems

Advancements in large language models (LLMs) have driven the emergence of complex new systems to provide access to information, that we will collectively refer to as modular generative information access (GenIA) systems. They integrate a broad and evolving range of specialized components, including LLMs, retrieval models, and a heterogeneous set of sources and tools. While modularity offers flexibility, it also raises critical challenges: How can we systematically characterize the space of possible modules and their interactions? How can we automate and optimize interactions among these heterogeneous components? And, how do we enable this modular system to dynamically adapt to varying user query requirements and evolving module capabilities? In this perspective paper, we argue that the architecture of future modular generative information access systems will not just assemble powerful components, but enable a self-organizing system through real-time adaptive orchestration -- where components' interactions are dynamically configured for each user input, maximizing information relevance while minimizing computational overhead. We give provisional answers to the questions raised above with a roadmap that depicts the key principles and methods for designing such an adaptive modular system. We identify pressing challenges, and propose avenues for addressing them in the years ahead. This perspective urges the IR community to rethink modular system designs for developing adaptive, self-optimizing, and future-ready architectures that evolve alongside their rapidly advancing underlying technologies.

Understanding Accuracy-Fairness Trade-offs in Re-ranking through Elasticity in Economics

Fairness is an increasingly important factor in re-ranking tasks. Prior work has identified a trade-off between ranking accuracy and item fairness. However, the underlying mechanisms are still not fully understood. An analogy can be drawn between re-ranking and the dynamics of economic transactions. The accuracy-fairness trade-off parallels the coupling of the commodity tax transfer process. Fairness considerations in re-ranking, similar to a commodity tax on suppliers, ultimately translate into a cost passed on to consumers. Analogously, item-side fairness constraints result in a decline in user-side accuracy. In economics, the extent to which commodity tax on the supplier (item fairness) transfers to commodity tax on users (accuracy loss) is formalized using the notion of elasticity. The re-ranking fairness-accuracy trade-off is similarly governed by the elasticity of utility between item groups. This insight underscores the limitations of current fair re-ranking evaluations, which often rely solely on a single fairness metric, hindering comprehensive assessment of fair re-ranking algorithms. Centered around the concept of elasticity, this work presents two significant contributions. We introduce the Elastic Fairness Curve (EF-Curve) as an evaluation framework. This framework enables a comparative analysis of algorithm performance across different elasticity levels, facilitating the selection of the most suitable approach. Furthermore, we propose ElasticRank, a fair re-ranking algorithm that employs elasticity calculations to adjust inter-item distances within a curved space. Experiments on three widely used ranking datasets demonstrate its effectiveness and efficiency.