Masoud Hashemi

Ga Wu, Masoud Hashemi, Christopher Srinivasa

Preserving the performance of a trained model while removing unique characteristics of marked training data points is challenging. Recent research usually suggests retraining a model from scratch with remaining training data or refining the model by reverting the model optimization on the marked data points. Unfortunately, aside from their computational inefficiency, those approaches inevitably hurt the resulting model's generalization ability since they remove not only unique characteristics but also discard shared (and possibly contributive) information. To address the performance degradation problem, this paper presents a novel approach called Performance Unchanged Model Augmentation~(PUMA). The proposed PUMA framework explicitly models the influence of each training data point on the model's generalization ability with respect to various performance criteria. It then complements the negative impact of removing marked data by reweighting the remaining data optimally. To demonstrate the effectiveness of the PUMA framework, we compared it with multiple state-of-the-art data removal techniques in the experiments, where we show the PUMA can effectively and efficiently remove the unique characteristics of marked training data without retraining the model that can 1) fool a membership attack, and 2) resist performance degradation. In addition, as PUMA estimates the data importance during its operation, we show it could serve to debug mislabelled data points more efficiently than existing approaches.

Nishanth Madhusudhan, Sathwik Tejaswi Madhusudhan, Vikas Yadav et al.

Abstention Ability (AA) is a critical aspect of Large Language Model (LLM) reliability, referring to an LLM's capability to withhold responses when uncertain or lacking a definitive answer, without compromising performance. Although previous studies have attempted to improve AA, they lack a standardised evaluation method and remain unsuitable for black-box models where token prediction probabilities are inaccessible. This makes comparative analysis challenging, especially for state-of-the-art closed-source commercial LLMs. This paper bridges this gap by introducing a black-box evaluation approach and a new dataset, Abstain-QA, crafted to rigorously assess AA across varied question types (answerable and unanswerable), domains (well-represented and under-represented), and task types (fact centric and reasoning). We also propose a new confusion matrix, the ''Answerable-Unanswerable Confusion Matrix'' (AUCM) which serves as the basis for evaluating AA, by offering a structured and precise approach for assessment. Finally, we explore the impact of three prompting strategies-Strict Prompting, Verbal Confidence Thresholding, and Chain-of-Thought (CoT)-on improving AA. Our results indicate that even powerful models like GPT-4, Mixtral 8x22b encounter difficulties with abstention; however, strategic approaches such as Strict prompting and CoT can enhance this capability.

Aman Tiwari, Shiva Krishna Reddy Malay, Vikas Yadav et al.

Graph databases like Neo4j are gaining popularity for handling complex, interconnected data, over traditional relational databases in modeling and querying relationships. While translating natural language into SQL queries is well-researched, generating Cypher queries for Neo4j remains relatively underexplored. In this work, we present an automated, LLM-Supervised, pipeline to generate high-quality synthetic data for Text2Cypher. Our Cypher data generation pipeline introduces LLM-As-Database-Filler, a novel strategy for ensuring Cypher query correctness, thus resulting in high quality generations. Using our pipeline, we generate high quality Text2Cypher data - SynthCypher containing 29.8k instances across various domains and queries with varying complexities. Training open-source LLMs like LLaMa-3.1-8B, Mistral-7B, and QWEN-7B on SynthCypher results in performance gains of up to 40% on the Text2Cypher test split and 30% on the SPIDER benchmark, adapted for graph databases.

Shruthan Radhakrishna, Aman Tiwari, Aanjaneya Shukla et al.

We present Apriel-1.5-15B-Thinker, a 15-billion parameter open-weights multimodal reasoning model that achieves frontier-level performance through training design rather than sheer scale. Starting from Pixtral-12B, we apply a progressive three-stage methodology: (1) depth upscaling to expand reasoning capacity without pretraining from scratch, (2) staged continual pre-training that first develops foundational text and vision understanding, then enhances visual reasoning through targeted synthetic data generation addressing spatial structure, compositional understanding, and fine-grained perception, and (3) high-quality text-only supervised fine-tuning on curated instruction-response pairs with explicit reasoning traces spanning mathematics, coding, science, and tool use. Notably, our model achieves competitive results without reinforcement learning or preference optimization, isolating the contribution of our data-centric continual pre-training approach. On the Artificial Analysis Intelligence Index, Apriel-1.5-15B-Thinker attains a score of 52, matching DeepSeek-R1-0528 despite requiring significantly fewer computational resources. Across ten image benchmarks, its performance is on average within five points of Gemini-2.5-Flash and Claude Sonnet-3.7, a key achievement for a model operating within single-GPU deployment constraints. Our results demonstrate that thoughtful mid-training 2 design can close substantial capability gaps without massive scale, making frontier-level multimodal reasoning accessible to organizations with limited infrastructure. We release the model checkpoint, all training recipes, and evaluation protocols under the MIT license to to advance open-source research.

Ahmed Masry, Abhay Puri, Masoud Hashemi et al. · mila

Charts are essential to data analysis, transforming raw data into clear visual representations that support human decision-making. Although current vision-language models (VLMs) have made significant progress, they continue to struggle with chart comprehension due to training on datasets that lack diversity and real-world authenticity, or on automatically extracted underlying data tables of charts, which can contain numerous estimation errors. Furthermore, existing models only rely on supervised fine-tuning using these low-quality datasets, severely limiting their effectiveness. To address these issues, we first propose BigCharts, a dataset creation pipeline that generates visually diverse chart images by conditioning the rendering process on real-world charts sourced from multiple online platforms. Unlike purely synthetic datasets, BigCharts incorporates real-world data, ensuring authenticity and visual diversity, while still retaining accurate underlying data due to our proposed replotting process. Additionally, we introduce a comprehensive training framework that integrates supervised fine-tuning with Group Relative Policy Optimization (GRPO)-based reinforcement learning. By introducing novel reward signals specifically designed for chart reasoning, our approach enhances model robustness and generalization across diverse chart styles and domains, resulting in a state-of-the-art chart reasoning model, BigCharts-R1. Extensive experiments demonstrate that our models surpass existing methods on multiple chart question-answering benchmarks compared to even larger open-source and closed-source models.

Masoud Hashemi, Oluwanifemi Bamgbose, Sathwik Tejaswi Madhusudhan et al.

Test-time scaling has significantly improved large language model performance, enabling deeper reasoning to solve complex problems. However, this increased reasoning capability also leads to excessive token generation and unnecessary problem-solving attempts. We introduce Dont Reason Bench (DNR Bench), a new benchmark designed to evaluate LLMs ability to robustly understand the tricky reasoning triggers and avoiding unnecessary generation. DNR Bench consists of 150 adversarially designed prompts that are easy for humans to understand and respond to, but surprisingly not for many of the recent prominent LLMs. DNR Bench tests models abilities across different capabilities, such as instruction adherence, hallucination avoidance, redundancy filtering, and unanswerable question recognition. We evaluate reasoning LLMs (RLMs), including DeepSeek-R1, OpenAI O3-mini, Claude-3.7-sonnet and compare them against a powerful non-reasoning model, e.g., GPT-4o. Our experiments reveal that RLMs generate up to 70x more tokens than necessary, often failing at tasks that simpler non-reasoning models handle efficiently with higher accuracy. Our findings underscore the need for more effective training and inference strategies in RLMs.

Hoang H Nguyen, Khyati Mahajan, Vikas Yadav et al.

Although multilingual LLMs have achieved remarkable performance across benchmarks, we find they continue to underperform on non-Latin script languages across contemporary LLM families. This discrepancy arises from the fact that LLMs are pretrained with orthographic scripts, which are dominated by Latin characters that obscure their shared phonology with non-Latin scripts. We propose leveraging phonemic transcriptions as complementary signals to induce script-invariant representations. Our study demonstrates that integrating phonemic signals improves performance across both non-Latin and Latin script languages, with a particularly significant impact on closing the performance gap between the two. Through detailed experiments, we show that phonemic and orthographic scripts retrieve distinct examples for in-context learning (ICL). This motivates our proposed Mixed-ICL retrieval strategy, where further aggregation from both leads to our significant performance improvements for both Latin script languages (up to 12.6%) and non-Latin script languages (up to 15.1%) compared to randomized ICL retrieval.

Shruthan Radhakrishna, Soham Parikh, Gopal Sarda et al.

While large language models (LLMs) have achieved remarkable reasoning capabilities across domains like code, math and other enterprise tasks, their significant memory and computational costs often preclude their use in practical enterprise settings. To this end, we introduce Apriel-Nemotron-15B-Thinker, a 15-billion parameter model in the ServiceNow Apriel SLM series that achieves performance against medium sized state-of-the-art models such as o1-mini, QWQ32B, and EXAONE-Deep-32B while maintaining only half the memory footprint of those alternatives. Apriel-Nemotron-15B-Thinker model is trained in a four stage training pipeline including 1) Base Model upscaling, 2) Continual Pre-training 3) Supervised Fine-tuning (SFT) and 4) Reinforcement Learning using GRPO. Comprehensive evaluations across a diverse suite of benchmarks consistently demonstrate that our Apriel-Nemotron-15B-Thinker model matches or exceeds the performance of its 32-billion parameter counterparts, despite being less than half their size.

Bryan Etzine, Masoud Hashemi, Nishanth Madhusudhan et al.

Existing benchmarks are becoming saturated and struggle to separate model performances due to factors like data contamination and advancing LLM capabilities. This paper introduces EMDM (Enhanced Model Differentiation Metric), a novel weighted metric that revitalizes benchmarks by enhancing model separation. EMDM integrates final answer and Chain-of-Thought (CoT) reasoning correctness, assigning weights based on the complexity and reasoning depth required to solve a given sample in the evaluation data. Using a baseline LLM in two setups-Unguided, where the model has no prior exposure to test samples, and Guided, where the model has prior knowledge of the desired answer-EMDM distinguishes instances of varying difficulty. The CoT and answer correctness from these setups inform an optimization objective for weight assignment, resulting in a more nuanced evaluation of model performance. Compared to the exact match (EM) metric, which achieves 17% separation on ARC-Challenge, EMDM achieves 46%, demonstrating its effectiveness in differentiating models based on reasoning and knowledge requirements.

Rishabh Maheshwary, Masoud Hashemi, Khyati Mahajan et al.

Iterative RAG for multi-hop question answering faces challenges with lengthy contexts and the buildup of irrelevant information. This hinders a model's capacity to process and reason over retrieved content and limits performance. While recent methods focus on compressing retrieved information, they are either restricted to single-round RAG, require finetuning or lack scalability in iterative RAG. To address these challenges, we propose Notes Writing, a method that generates concise and relevant notes from retrieved documents at each step, thereby reducing noise and retaining only essential information. This indirectly increases the effective context length of Large Language Models (LLMs), enabling them to reason and plan more effectively while processing larger volumes of input text. Notes Writing is framework agnostic and can be integrated with different iterative RAG methods. We demonstrate its effectiveness with three iterative RAG methods, across two models and four evaluation datasets. Notes writing yields an average improvement of 15.6 percentage points overall, with minimal increase in output tokens.

Giuseppe Castiglione, Gavin Ding, Masoud Hashemi et al.

Adversarial robustness is one of the essential safety criteria for guaranteeing the reliability of machine learning models. While various adversarial robustness testing approaches were introduced in the last decade, we note that most of them are incompatible with non-differentiable models such as tree ensembles. Since tree ensembles are widely used in industry, this reveals a crucial gap between adversarial robustness research and practical applications. This paper proposes a novel whitebox adversarial robustness testing approach for tree ensemble models. Concretely, the proposed approach smooths the tree ensembles through temperature controlled sigmoid functions, which enables gradient descent-based adversarial attacks. By leveraging sampling and the log-derivative trick, the proposed approach can scale up to testing tasks that were previously unmanageable. We compare the approach against both random perturbations and blackbox approaches on multiple public datasets (and corresponding models). Our results show that the proposed method can 1) successfully reveal the adversarial vulnerability of tree ensemble models without causing computational pressure for testing and 2) flexibly balance the search performance and time complexity to meet various testing criteria.

Masoud Hashemi, Ali Fathi

This paper is a note on new directions and methodologies for validation and explanation of Machine Learning (ML) models employed for retail credit scoring in finance. Our proposed framework draws motivation from the field of Artificial Intelligence (AI) security and adversarial ML where the need for certifying the performance of the ML algorithms in the face of their overwhelming complexity poses a need for rethinking the traditional notions of model architecture selection, sensitivity analysis and stress testing. Our point of view is that the phenomenon of adversarial perturbations when detached from the AI security domain, has purely algorithmic roots and fall within the scope of model risk assessment. We propose a model criticism and explanation framework based on adversarially generated counterfactual examples for tabular data. A counterfactual example to a given instance in this context is defined as a synthetically generated data point sampled from the estimated data distribution which is treated differently by a model. The counterfactual examples can be used to provide a black-box instance-level explanation of the model behaviour as well as studying the regions in the input space where the model performance deteriorates. Adversarial example generating algorithms are extensively studied in the image and natural language processing (NLP) domains. However, most financial data come in tabular format and naive application of the existing techniques on this class of datasets generates unrealistic samples. In this paper, we propose a counterfactual example generation method capable of handling tabular data including discrete and categorical variables. Our proposed algorithm uses a gradient-free optimization based on genetic algorithms and therefore is applicable to any classification model.

Greg Kirczenow, Masoud Hashemi, Ali Fathi et al.

This paper studies an application of machine learning in extracting features from the historical market implied corporate bond yields. We consider an example of a hypothetical illiquid fixed income market. After choosing a surrogate liquid market, we apply the Denoising Autoencoder (DAE) algorithm to learn the features of the missing yield parameters from the historical data of the instruments traded in the chosen liquid market. The DAE algorithm is then challenged by two "point-in-time" inpainting algorithms taken from the image processing and computer vision domain. It is observed that, when tested on unobserved rate surfaces, the DAE algorithm exhibits superior performance thanks to the features it has learned from the historical shapes of yield curves.