arXiv subjects

Faegheh Hasibi

Publications and source records attributed to Faegheh Hasibi.

At least 19 recordsLinked to original sources

arXiv2026

When Deep Research Agents Stagnate: Enhancing Reasoning with Retrieval-Aware Agent Control

In this paper, we analyze the reasoning trajectories of a variety of DRAs and show that existing agents often suffer from reasoning stagnation: the majority of iterations contribute little or no improvement to final performance, while agents lack awareness of their trajectories and are therefore ineffective at adapting their search strategies or determining when to terminate. To address this issue, we introduce a set of unsupervised signals and a Retrieval-Aware Agent Controller (RAAC), which assists the agent in selecting optimal actions at each stage of the research process. RAAC incorporates key information retrieval principles, namely search novelty and information coverage, resulting in more effective reasoning trajectories that improve overall performance while reducing unnecessary iterations, and consequently cost and latency. Specifically on BrowseComp-Plus and across a large set of DRAs, adding RAAC reduces the number of search calls by an average of 14, significantly improves the best-performing DRA on recall and accuracy, and achieves an accuracy gain of up to 10% (3% on average).

cs.IR↗

arXiv2026

Uncertainty Quantification for Multimodal Retrieval Augmented Generation

Retrieval Augmented Generation (RAG) improves the question answering capabilities of Large Language Models (LLMs) by incorporating external knowledge and has recently been extended to multimodal settings through Vision-Language Models (VLMs) that integrate visual and textual information. Despite these advances, generated answers can still be incorrect or misleading. Uncertainty Quantification (UQ) methods aim to estimate the reliability of model outputs, but most existing approaches are designed for text-only models and perform poorly in multimodal RAG scenarios. A key challenge is capturing uncertainty arising from multiple stages of the pipeline, including retrieval, visual understanding, and generation. In this work, we show that modeling uncertainty using multimodal and retrieval-aware probability signals improves estimation in multimodal RAG systems. We introduce LeMUQ, a Learnable Multimodal UQ method that analyzes token probabilities under input modifications, such as removing modalities or retrieved context. By encoding these signals as probability tokens and processing them with a finetuned model, our approach captures interactions between modalities and retrieval. Experiments across datasets, retrievers, and VLMs show consistent improvements over baseline and finetuned UQ methods. Our proposed LeMUQ increases the AUROC metric by 3.8% on average. Additionally, our method shows strong generalization performance across different retrieval setups and datasets with mixed results when transferring across different VLMs. Our findings highlight the importance of modeling multimodal uncertainty and provide a step toward more reliable and safer multimodal RAG systems. Code is available on GitHub.

cs.IR↗

arXiv2026

Reproducing Complex Set-Compositional Information Retrieval

Complex information needs may involve set-compositional queries using conjunction, disjunction, and exclusion, yet it remains unclear whether current retrieval paradigms genuinely satisfy such constraints or exploit `semantic shortcuts'. We conduct a reproducibility study to benchmark major retrieval families and reasoning-targeted methods on QUEST and QUEST+Variants, and introduce LIMIT+, a controlled benchmark where relevance depends on arbitrary attribute predicates and constraint satisfaction, and less on pretrained knowledge. Our findings show that (i) on QUEST, the best neural retrievers achieve an effectiveness that is more than double what can be achieved with BM25 (Recall@100 ${>}$0.41 vs.\ 0.20), but reasoning-targeted methods like ReasonIR and Search-R1 do not outperform general-purpose retrievers uniformly; (ii) on LIMIT+, gains fail to transfer, where the strongest QUEST method collapses from Recall@100${\approx}$0.42 to below 0.02, while classic lexical retrieval gains to ${\sim}$0.96. Lastly, (iii) stratifying by compositional depth reveals a consistent degradation across all methods, where algebraic sparse and lexical methods show more stable performance while dense approaches collapse. We release code and LIMIT+ data generation scripts to support future reproducibility and controlled evaluation.

cs.CL↗

arXiv2026

Total Recall QA: A Verifiable Evaluation Suite for Deep Research Agents

Deep research agents have emerged as LLM-based systems designed to perform multi-step information seeking and reasoning over large, open-domain sources to answer complex questions by synthesizing information from multiple information sources. Given the complexity of the task and despite various recent efforts, evaluation of deep research agents remains fundamentally challenging. This paper identifies a list of requirements and optional properties for evaluating deep research agents. We observe that existing benchmarks do not satisfy all identified requirements. Inspired by prior research on TREC Total Recall Tracks, we introduce the task of Total Recall Question Answering and develop a framework for deep research agents evaluation that satisfies the identified criteria. Our framework constructs single-answer, total recall queries with precise evaluation and relevance judgments derived from a structured knowledge base paired with a text corpus, enabling large-scale data construction. Using this framework, we build TRQA, a deep research benchmark constructed from Wikidata-Wikipedia as a real-world source and a synthetically generated e-commerce knowledge base and corpus to mitigate the effects of data contamination. We benchmark the collection with representative retriever and deep research models and establish baseline retrieval and end-to-end results for future comparative evaluation.

cs.IR↗

arXiv2026

OrLog: Resolving Complex Queries with LLMs and Probabilistic Reasoning

Resolving complex information needs that come with multiple constraints should consider enforcing the logical operators encoded in the query (i.e., conjunction, disjunction, negation) on the candidate answer set. Current retrieval systems either ignore these constraints in neural embeddings or approximate them in a generative reasoning process that can be inconsistent and unreliable. Although well-suited to structured reasoning, existing neuro-symbolic approaches remain confined to formal logic or mathematics problems as they often assume unambiguous queries and access to complete evidence, conditions rarely met in information retrieval. To bridge this gap, we introduce OrLog, a neuro-symbolic retrieval framework that decouples predicate-level plausibility estimation from logical reasoning: a large language model (LLM) provides plausibility scores for atomic predicates in one decoding-free forward pass, from which a probabilistic reasoning engine derives the posterior probability of query satisfaction. We evaluate OrLog across multiple backbone LLMs, varying levels of access to external knowledge, and a range of logical constraints, and compare it against base retrievers and LLM-as-reasoner methods. Provided with entity descriptions, OrLog can significantly boost top-rank precision compared to LLM reasoning with larger gains on disjunctive queries. OrLog is also more efficient, cutting mean tokens by $\sim$90\% per query-entity pair. These results demonstrate that generation-free predicate plausibility estimation combined with probabilistic reasoning enables constraint-aware retrieval that outperforms monolithic reasoning while using far fewer tokens.

cs.IR↗

arXiv2025

LUMI: Unsupervised Intent Clustering with Multiple Pseudo-Labels

In this paper, we propose an intuitive, training-free and label-free method for intent clustering in conversational search. Current approaches to short text clustering use LLM-generated pseudo-labels to enrich text representations or to identify similar text pairs for pooling. The limitations are: (1) each text is assigned only a single label, and refining representations toward a single label can be unstable; (2) text-level similarity is treated as a binary selection, which fails to account for continuous degrees of similarity. Our method LUMI is designed to amplify similarities between texts by using shared pseudo-labels. We first generate pseudo-labels for each text and collect them into a pseudo-label set. Next, we compute the mean of the pseudo-label embeddings and pool it with the text embedding. Finally, we perform text-level pooling: Each text representation is pooled with its similar pairs, where similarity is determined by the degree of shared labels. Our evaluation on four benchmark sets shows that our approach achieves competitive results, better than recent state-of-the-art baselines, while avoiding the need to estimate the number of clusters during embedding refinement, as is required by most methods. Our findings indicate that LUMI can effectively be applied in unsupervised short-text clustering scenarios.

cs.CL↗

arXiv2025

Uncertainty Quantification for Retrieval-Augmented Reasoning

Retrieval-augmented reasoning (RAR) is a recent evolution of retrieval-augmented generation (RAG) that employs multiple reasoning steps for retrieval and generation. While effective for some complex queries, RAR remains vulnerable to errors and misleading outputs. Uncertainty quantification (UQ) offers methods to estimate the confidence of systems' outputs. These methods, however, often handle simple queries with no retrieval or single-step retrieval, without properly handling RAR setup. Accurate estimation of UQ for RAR requires accounting for all sources of uncertainty, including those arising from retrieval and generation. In this paper, we account for all these sources and introduce Retrieval-Augmented Reasoning Consistency (R2C)--a novel UQ method for RAR. The core idea of R2C is to perturb the multi-step reasoning process by applying various actions to reasoning steps. These perturbations alter the retriever's input, which shifts its output and consequently modifies the generator's input at the next step. Through this iterative feedback loop, the retriever and generator continuously reshape one another's inputs, enabling us to capture uncertainty arising from both components. Experiments on five popular RAR systems across diverse QA datasets show that R2C improves AUROC by over 5% on average compared to the state-of-the-art UQ baselines. Extrinsic evaluations using R2C as an external signal further confirm its effectiveness for two downstream tasks: in Abstention, it achieves ~5% gains in both F1Abstain and AccAbstain; in Model Selection, it improves the exact match by ~7% over single models and ~3% over selection methods.

cs.IR↗

arXiv2025

LLMs Enable Bag-of-Texts Representations for Short-Text Clustering

In this paper, we propose a training-free method for unsupervised short text clustering that relies less on careful selection of embedders than other methods. In customer-facing chatbots, companies are dealing with large amounts of user utterances that need to be clustered according to their intent. In these settings, no labeled data is typically available, and the number of clusters is not known. Recent approaches to short-text clustering in label-free settings incorporate LLM output to refine existing embeddings. While LLMs can identify similar texts effectively, the resulting similarities may not be directly represented by distances in the dense vector space, as they depend on the original embedding. We therefore propose a method for transforming LLM judgments directly into a bag-of-texts representation in which texts are initialized to be equidistant, without assuming any prior distance relationships. Our method achieves comparable or superior results to state-of-the-art methods, but without embeddings optimization or assuming prior knowledge of clusters or labels. Experiments on diverse datasets and smaller LLMs show that our method is model agnostic and can be applied to any embedder, with relatively small LLMs, and different clustering methods. We also show how our method scales to large datasets, reducing the computational cost of the LLM use. The flexibility and scalability of our method make it more aligned with real-world training-free scenarios than existing clustering methods.

cs.CL↗

arXiv2025

WildClaims: Information Access Conversations in the Wild(Chat)

The rapid advancement of Large Language Models (LLMs) has transformed conversational systems into practical tools used by millions. However, the nature and necessity of information retrieval in real-world conversations remain largely unexplored, as research has focused predominantly on traditional, explicit information access conversations. The central question is: What do real-world information access conversations look like? To this end, we first conduct an observational study on the WildChat dataset, large-scale user-ChatGPT conversations, finding that users' access to information occurs implicitly as check-worthy factual assertions made by the system, even when the conversation's primary intent is non-informational, such as creative writing. To enable the systematic study of this phenomenon, we release the WildClaims dataset, a novel resource consisting of 121,905 extracted factual claims from 7,587 utterances in 3,000 WildChat conversations, each annotated for check-worthiness. Our preliminary analysis of this resource reveals that conservatively 18% to 51% of conversations contain check-worthy assertions, depending on the methods employed, and less conservatively, as many as 76% may contain such assertions. This high prevalence underscores the importance of moving beyond the traditional understanding of explicit information access, to address the implicit information access that arises in real-world user-system conversations.

cs.IR↗

arXiv2025

Towards a Large Physics Benchmark

We introduce a benchmark framework developed by and for the scientific community to evaluate, monitor and steer large language model development in fundamental physics. Building on philosophical concepts of scientific understanding and creativity, we develop a scoring system in which each question is scored by an expert for its correctness, difficulty, and surprise. The questions are of three forms: (i) multiple-choice questions for conceptual understanding, (ii) analytical problems requiring mathematical derivation, and (iii) openended tasks requiring complex problem solving. Our current dataset contains diverse set of examples, including a machine learning challenge to classify high-energy physics events, such as the four top quark signal. To ensure continued relevance, we propose a living benchmark, where physicists contribute questions, for instance alongside new publications. We invite contributions via: http://www.physicsbenchmarks.org/. We hope that this benchmark will enable a targeted AI development that can make a meaningful contribution to fundamental physics research.

physics.data-an↗

arXiv2025

PromptAug: Fine-grained Conflict Classification Using Data Augmentation

Given the rise of conflicts on social media, effective classification models to detect harmful behaviours are essential. Following the garbage-in-garbage-out maxim, machine learning performance depends heavily on training data quality. However, high-quality labelled data, especially for nuanced tasks like identifying conflict behaviours, is limited, expensive, and difficult to obtain. Additionally, as social media platforms increasingly restrict access to research data, text data augmentation is gaining attention as an alternative to generate training data. Augmenting conflict-related data poses unique challenges due to Large Language Model (LLM) guardrails that prevent generation of offensive content. This paper introduces PromptAug, an innovative LLM-based data augmentation method. PromptAug achieves statistically significant improvements of 2% in both accuracy and F1-score on conflict and emotion datasets. To thoroughly evaluate PromptAug against other data augmentation methods we conduct a robust evaluation using extreme data scarcity scenarios, quantitative diversity analysis and a qualitative thematic analysis. The thematic analysis identifies four problematic patterns in augmented text: Linguistic Fluidity, Humour Ambiguity, Augmented Content Ambiguity, and Augmented Content Misinterpretation. Overall, this work presents PromptAug as an effective method for augmenting data in sensitive tasks like conflict detection, offering a unique, interdisciplinary evaluation grounded in both natural language processing and social science methodology.

cs.CL↗

arXiv2025

Graph-Embedding Empowered Entity Retrieval

In this research, we investigate methods for entity retrieval using graph embeddings. While various methods have been proposed over the years, most utilize a single graph embedding and entity linking approach. This hinders our understanding of how different graph embedding and entity linking methods impact entity retrieval. To address this gap, we investigate the effects of three different categories of graph embedding techniques and five different entity linking methods. We perform a reranking of entities using the distance between the embeddings of annotated entities and the entities we wish to rerank. We conclude that the selection of both graph embeddings and entity linkers significantly impacts the effectiveness of entity retrieval. For graph embeddings, methods that incorporate both graph structure and textual descriptions of entities are the most effective. For entity linking, both precision and recall concerning concepts are important for optimal retrieval performance. Additionally, it is essential for the graph to encompass as many entities as possible.

cs.IR↗

arXiv2025

FACE: A Fine-Grained Reference-Free Evaluator for Conversational Information Access

A systematic, reliable, and low-cost evaluation of Conversational Information Access (CIA) systems remains an open challenge. Existing reference-based evaluation methods are proven insufficient for evaluating the dynamic nature of information access conversations, while existing LLM-based reference-free methods suffer from evaluation bias and limited generalizability. This work proposes FACE: a Fine-grained, Aspect-based Conversation Evaluation method that provides evaluation scores for diverse turn and dialogue-level aspects of conversations. FACE leverages beam search and bandit optimization to select optimized LLM instructions per evaluation aspect. It assigns scores to atomic information units (particles) using the selected instructions and then aggregates them into a single score. We show that FACE achieves a strong correlation with human judgments, achieving system correlation of 0.9, outperforming state-of-the-art conversation evaluation methods by a large margin. We further demonstrate its optimized instructions are transferable across various LLMs and datasets. Additionally, unlike existing LLM-based methods that provide single uninterpretable scores, FACE provides insights into the system performance and enables identifying and locating problems within conversations.

cs.IR↗

arXiv2025

Why Uncertainty Estimation Methods Fall Short in RAG: An Axiomatic Analysis

Large Language Models (LLMs) are valued for their strong performance across various tasks, but they also produce inaccurate or misleading outputs. Uncertainty Estimation (UE) quantifies the model's confidence and helps users assess response reliability. However, existing UE methods have not been thoroughly examined in scenarios like Retrieval-Augmented Generation (RAG), where the input prompt includes non-parametric knowledge. This paper shows that current UE methods cannot reliably assess correctness in the RAG setting. We further propose an axiomatic framework to identify deficiencies in existing methods and guide the development of improved approaches. Our framework introduces five constraints that an effective UE method should meet after incorporating retrieved documents into the LLM's prompt. Experimental results reveal that no existing UE method fully satisfies all the axioms, explaining their suboptimal performance in RAG. We further introduce a simple yet effective calibration function based on our framework, which not only satisfies more axioms than baseline methods but also improves the correlation between uncertainty estimates and correctness.

cs.IR↗

arXiv2025

LLM-Evaluation Tropes: Perspectives on the Validity of LLM-Evaluations

Large Language Models (LLMs) are increasingly used to evaluate information retrieval (IR) systems, generating relevance judgments traditionally made by human assessors. Recent empirical studies suggest that LLM-based evaluations often align with human judgments, leading some to suggest that human judges may no longer be necessary, while others highlight concerns about judgment reliability, validity, and long-term impact. As IR systems begin incorporating LLM-generated signals, evaluation outcomes risk becoming self-reinforcing, potentially leading to misleading conclusions. This paper examines scenarios where LLM-evaluators may falsely indicate success, particularly when LLM-based judgments influence both system development and evaluation. We highlight key risks, including bias reinforcement, reproducibility challenges, and inconsistencies in assessment methodologies. To address these concerns, we propose tests to quantify adverse effects, guardrails, and a collaborative framework for constructing reusable test collections that integrate LLM judgments responsibly. By providing perspectives from academia and industry, this work aims to establish best practices for the principled use of LLMs in IR evaluation.

cs.IR↗

arXiv2025

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.

cs.IR↗

arXiv2025

SPILL: Domain-Adaptive Intent Clustering based on Selection and Pooling with Large Language Models

In this paper, we propose Selection and Pooling with Large Language Models (SPILL), an intuitive and domain-adaptive method for intent clustering without fine-tuning. Existing embeddings-based clustering methods rely on a few labeled examples or unsupervised fine-tuning to optimize results for each new dataset, which makes them less generalizable to multiple datasets. Our goal is to make these existing embedders more generalizable to new domain datasets without further fine-tuning. Inspired by our theoretical derivation and simulation results on the effectiveness of sampling and pooling techniques, we view the clustering task as a small-scale selection problem. A good solution to this problem is associated with better clustering performance. Accordingly, we propose a two-stage approach: First, for each utterance (referred to as the seed), we derive its embedding using an existing embedder. Then, we apply a distance metric to select a pool of candidates close to the seed. Because the embedder is not optimized for new datasets, in the second stage, we use an LLM to further select utterances from these candidates that share the same intent as the seed. Finally, we pool these selected candidates with the seed to derive a refined embedding for the seed. We found that our method generally outperforms directly using an embedder, and it achieves comparable results to other state-of-the-art studies, even those that use much larger models and require fine-tuning, showing its strength and efficiency. Our results indicate that our method enables existing embedders to be further improved without additional fine-tuning, making them more adaptable to new domain datasets. Additionally, viewing the clustering task as a small-scale selection problem gives the potential of using LLMs to customize clustering tasks according to the user's goals.

cs.CL↗

arXiv2025

Large Physics Models: Towards a collaborative approach with Large Language Models and Foundation Models

This paper explores ideas and provides a potential roadmap for the development and evaluation of physics-specific large-scale AI models, which we call Large Physics Models (LPMs). These models, based on foundation models such as Large Language Models (LLMs) - trained on broad data - are tailored to address the demands of physics research. LPMs can function independently or as part of an integrated framework. This framework can incorporate specialized tools, including symbolic reasoning modules for mathematical manipulations, frameworks to analyse specific experimental and simulated data, and mechanisms for synthesizing theories and scientific literature. We begin by examining whether the physics community should actively develop and refine dedicated models, rather than relying solely on commercial LLMs. We then outline how LPMs can be realized through interdisciplinary collaboration among experts in physics, computer science, and philosophy of science. To integrate these models effectively, we identify three key pillars: Development, Evaluation, and Philosophical Reflection. Development focuses on constructing models capable of processing physics texts, mathematical formulations, and diverse physical data. Evaluation assesses accuracy and reliability by testing and benchmarking. Finally, Philosophical Reflection encompasses the analysis of broader implications of LLMs in physics, including their potential to generate new scientific understanding and what novel collaboration dynamics might arise in research. Inspired by the organizational structure of experimental collaborations in particle physics, we propose a similarly interdisciplinary and collaborative approach to building and refining Large Physics Models. This roadmap provides specific objectives, defines pathways to achieve them, and identifies challenges that must be addressed to realise physics-specific large scale AI models.

physics.data-an↗