Heydar Soudani

Heydar Soudani, Hamed Zamani, Faegheh Hasibi

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.

Simon Binz, Heydar Soudani, Faegheh Hasibi

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.

Heydar Soudani, Evangelos Kanoulas, Faegheh Hasibi

Advancements in conversational systems have revolutionized information access, surpassing the limitations of single queries. However, developing dialogue systems requires a large amount of training data, which is a challenge in low-resource domains and languages. Traditional data collection methods like crowd-sourcing are labor-intensive and time-consuming, making them ineffective in this context. Data augmentation (DA) is an affective approach to alleviate the data scarcity problem in conversational systems. This tutorial provides a comprehensive and up-to-date overview of DA approaches in the context of conversational systems. It highlights recent advances in conversation augmentation, open domain and task-oriented conversation generation, and different paradigms of evaluating these models. We also discuss current challenges and future directions in order to help researchers and practitioners to further advance the field in this area.

Heydar Soudani, Mohammad Hassan Mojab, Hamid Beigy

Incorporating information from other languages can improve the results of tasks in low-resource languages. A powerful method of building functional natural language processing systems for low-resource languages is to combine multilingual pre-trained representations with cross-lingual transfer learning. In general, however, shared representations are learned separately, either across tasks or across languages. This paper proposes a meta-learning approach for inferring natural language in Persian. Alternately, meta-learning uses different task information (such as QA in Persian) or other language information (such as natural language inference in English). Also, we investigate the role of task augmentation strategy for forming additional high-quality tasks. We evaluate the proposed method using four languages and an auxiliary task. Compared to the baseline approach, the proposed model consistently outperforms it, improving accuracy by roughly six percent. We also examine the effect of finding appropriate initial parameters using zero-shot evaluation and CCA similarity.

Heydar Soudani, Evangelos Kanoulas, Faegheh Hasibi

Language Models (LMs) memorize a vast amount of factual knowledge, exhibiting strong performance across diverse tasks and domains. However, it has been observed that the performance diminishes when dealing with less-popular or low-frequency concepts and entities, for example in domain specific applications. The two prominent approaches to enhance the performance of LMs on low-frequent topics are: Retrieval Augmented Generation (RAG) and fine-tuning (FT) over synthetic data. This paper explores and evaluates the impact of RAG and FT on customizing LMs in handling low-frequency entities on question answering tasks. We conduct extensive experiments on twelve LMs of varying size and type and different fine tuning, data augmentation, and retrieval models. Our findings indicate that while FT boosts the performance across entities of varying popularity, RAG surpasses FT by a large margin particularly for least popular factual knowledge. Additionally, the success of both RAG and FT approaches is amplified by improving retrieval and data augmentation techniques. Fine tuning, while beneficial for small LMs, requires extensive resources. To address this issue, we propose the new Stimulus RAG approach that surpasses the effectiveness of fine tuning based approaches, thereby eliminating the need for the costly data augmentation and fine tuning step for enriching LMs with less popular factual knowledge. The code is available at \url{https://github.com/informagi/RAGvsFT}.

Mahta Rafiee, Heydar Soudani, Zahra Abbasiantaeb et al.

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.

Zahra Moti, Heydar Soudani, Jonck van der Kogel

Modernizing large legacy systems remains a major challenge in enterprise environments, particularly when migration must preserve domain-specific logic while conforming to internal architectural frameworks and shared APIs. Direct application of Large Language Models (LLMs) for code translation often produces syntactically valid outputs that fail to compile or integrate within existing production frameworks, limiting their practical adoption in real-world modernization efforts. In this paper, we propose LegacyTranslate, a multi-agent framework for API-aware code translation, developed and evaluated in the context of an ongoing modernization effort at a financial institution migrating approximately 2.5 million lines of PL/SQL to Java. The core idea is to use specialized LLM-based agents, each addressing a different aspect of the translation challenge. Specifically, LegacyTranslate consists of three agents: Initial Translation Agent produces an initial Java translation using retrieved in-context examples; API Grounding Agent aligns the code with existing APIs by retrieving relevant entries from an API knowledge base; and Refinement Agent iteratively refines the output using compiler feedback and API suggestions to improve correctness. Our experiments show that each agent contributes to better translation quality. The Initial Translation Agent alone achieves 45.6% compilable outputs and 30.9% test-pass rate. With API Grounding Agent and Refinement Agent, compilation improves by an additional 8% and test-pass accuracy increases by 3%.

Heydar Soudani, Roxana Petcu, Evangelos Kanoulas et al.

Recent advancements in conversational systems have significantly enhanced human-machine interactions across various domains. However, training these systems is challenging due to the scarcity of specialized dialogue data. Traditionally, conversational datasets were created through crowdsourcing, but this method has proven costly, limited in scale, and labor-intensive. As a solution, the development of synthetic dialogue data has emerged, utilizing techniques to augment existing datasets or convert textual resources into conversational formats, providing a more efficient and scalable approach to dataset creation. In this survey, we offer a systematic and comprehensive review of multi-turn conversational data generation, focusing on three types of dialogue systems: open domain, task-oriented, and information-seeking. We categorize the existing research based on key components like seed data creation, utterance generation, and quality filtering methods, and introduce a general framework that outlines the main principles of conversation data generation systems. Additionally, we examine the evaluation metrics and methods for assessing synthetic conversational data, address current challenges in the field, and explore potential directions for future research. Our goal is to accelerate progress for researchers and practitioners by presenting an overview of state-of-the-art methods and highlighting opportunities to further research in this area.

Ali Samadzadeh, Mohammad Hassan Mojab, Heydar Soudani et al.

Visual Inertial Odometry (VIO) algorithms estimate the accurate camera trajectory by using camera and Inertial Measurement Unit (IMU) sensors. The applications of VIO span a diverse range, including augmented reality and indoor navigation. VIO algorithms hold the potential to facilitate navigation for visually impaired individuals in both indoor and outdoor settings. Nevertheless, state-of-the-art VIO algorithms encounter substantial challenges in dynamic environments, particularly in densely populated corridors. Existing VIO datasets, e.g., ADVIO, typically fail to effectively exploit these challenges. In this paper, we introduce the Amirkabir campus dataset (AUT-VI) to address the mentioned problem and improve the navigation systems. AUT-VI is a novel and super-challenging dataset with 126 diverse sequences in 17 different locations. This dataset contains dynamic objects, challenging loop-closure/map-reuse, different lighting conditions, reflections, and sudden camera movements to cover all extreme navigation scenarios. Moreover, in support of ongoing development efforts, we have released the Android application for data capture to the public. This allows fellow researchers to easily capture their customized VIO dataset variations. In addition, we evaluate state-of-the-art Visual Inertial Odometry (VIO) and Visual Odometry (VO) methods on our dataset, emphasizing the essential need for this challenging dataset.