Mandar Sharma
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Mandar Sharma has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Naren Ramakrishnan
Virginia Tech, Alexandria, USA
7 shared publications - Nikhil Muralidhar
Department of Computer Science Stevens Institute of Technology Hoboken NJ USA
3 shared publications - Andrew Neeser
Virginia Tech
2 shared publications - Chris Latimer
Vectorize.io
2 shared publications Naren Ramakrishnan
2 shared publications- Raquib Bin Yousuf
Virginia Tech Virginia USA
2 shared publications
Latest Publications
- 25 March 2026
- Published by Springer Nature
- p. 305-319
Utilizing Metadata for Better Retrieval-Augmented Generation
- 25 March 2026
- Published by Springer Nature
- p. 305-319
Utilizing Metadata for Better Retrieval-Augmented Generation
- Open Access
Utilizing Metadata for Better Retrieval-Augmented Generation
Retrieval-Augmented Generation systems depend on retrieving semantically relevant document chunks to support accurate, grounded outputs from large language models. In structured and repetitive corpora such as regulatory filings, chunk similarity alone often fails to distinguish between documents with overlapping language. Practitioners often flatten metadata into input text as a heuristic, but the impact and trade-offs of this practice remain poorly understood. We present a systematic study of metadata-aware retrieval strategies, comparing plain-text baselines with approaches that embed metadata directly. Our evaluation spans metadata-as-text (prefix and suffix), a dual-encoder unified embedding that fuses metadata and content in a single index, dual-encoder late-fusion retrieval, and metadata-aware query reformulation. Across multiple retrieval metrics and question types, we find that prefixing and unified embeddings consistently outperform plain-text baselines, with the unified at times exceeding prefixing while being easier to maintain. Beyond empirical comparisons, we analyze embedding space, showing that metadata integration improves effectiveness by increasing intra-document cohesion, reducing inter-document confusion, and widening the separation between relevant and irrelevant chunks. Field-level ablations show that structural cues provide strong disambiguating signals. Our code, evaluation framework, and the RAGMATE-10K dataset are publicly hosted.
Open AccessUtilizing Metadata for Better Retrieval-Augmented Generation
Retrieval-Augmented Generation systems depend on retrieving semantically relevant document chunks to support accurate, grounded outputs from large language models. In structured and repetitive corpora such as regulatory filings, chunk similarity alone often fails to distinguish between documents with overlapping language. Practitioners often flatten metadata into input text as a heuristic, but the impact and trade-offs of this practice remain poorly understood. We present a systematic study of metadata-aware retrieval strategies, comparing plain-text baselines with approaches that embed metadata directly. Our evaluation spans metadata-as-text (prefix and suffix), a dual-encoder unified embedding that fuses metadata and content in a single index, dual-encoder late-fusion retrieval, and metadata-aware query reformulation. Across multiple retrieval metrics and question types, we find that prefixing and unified embeddings consistently outperform plain-text baselines, with the unified at times exceeding prefixing while being easier to maintain. Beyond empirical comparisons, we analyze embedding space, showing that metadata integration improves effectiveness by increasing intra-document cohesion, reducing inter-document confusion, and widening the separation between relevant and irrelevant chunks. Field-level ablations show that structural cues provide strong disambiguating signals. Our code, evaluation framework, and the RAGMATE-10K dataset are publicly hosted.
- Open Access
- 17 October 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Intelligent Systems and Technology
- Vol. 15 (5) , 1-46
Neural Methods for Data-to-text Generation
The neural boom that has sparked natural language processing (NLP) research throughout the last decade has similarly led to significant innovations in data-to-text (D2T) generation. This survey offers a consolidated view into the neural D2T paradigm with a structured examination of the approaches, benchmark datasets, and evaluation protocols. This survey draws boundaries separating D2T from the rest of the natural language generation (NLG) landscape, encompassing an up-to-date synthesis of the literature, and highlighting the stages of technological adoption from within and outside the greater NLG umbrella. With this holistic view, we highlight promising avenues for D2T research that focus not only on the design of linguistically capable systems but also on systems that exhibit fairness and accountability.
- 17 October 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Intelligent Systems and Technology
- Vol. 15 (5) , 1-46
Open AccessNeural Methods for Data-to-text Generation
The neural boom that has sparked natural language processing (NLP) research throughout the last decade has similarly led to significant innovations in data-to-text (D2T) generation. This survey offers a consolidated view into the neural D2T paradigm with a structured examination of the approaches, benchmark datasets, and evaluation protocols. This survey draws boundaries separating D2T from the rest of the natural language generation (NLG) landscape, encompassing an up-to-date synthesis of the literature, and highlighting the stages of technological adoption from within and outside the greater NLG umbrella. With this holistic view, we highlight promising avenues for D2T research that focus not only on the design of linguistically capable systems but also on systems that exhibit fairness and accountability.
- Open Access
Innovations in Neural Data-to-text Generation: A Survey
The neural boom that has sparked natural language processing (NLP) research through the last decade has similarly led to significant innovations in data-to-text generation (DTG). This survey offers a consolidated view into the neural DTG paradigm with a structured examination of the approaches, benchmark datasets, and evaluation protocols. This survey draws boundaries separating DTG from the rest of the natural language generation (NLG) landscape, encompassing an up-to-date synthesis of the literature, and highlighting the stages of technological adoption from within and outside the greater NLG umbrella. With this holistic view, we highlight promising avenues for DTG research that not only focus on the design of linguistically capable systems but also systems that exhibit fairness and accountability.
Open AccessInnovations in Neural Data-to-text Generation: A Survey
The neural boom that has sparked natural language processing (NLP) research through the last decade has similarly led to significant innovations in data-to-text generation (DTG). This survey offers a consolidated view into the neural DTG paradigm with a structured examination of the approaches, benchmark datasets, and evaluation protocols. This survey draws boundaries separating DTG from the rest of the natural language generation (NLG) landscape, encompassing an up-to-date synthesis of the literature, and highlighting the stages of technological adoption from within and outside the greater NLG umbrella. With this holistic view, we highlight promising avenues for DTG research that not only focus on the design of linguistically capable systems but also systems that exhibit fairness and accountability.
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 2653-2660
Laying Anchors: Semantically Priming Numerals in Language Modeling
Mandar Sharma, Rutuja Taware, Pravesh Koirala, Nikhil Muralidhar, Naren Ramakrishnan. Findings of the Association for Computational Linguistics: NAACL 2024. 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 2653-2660
Open AccessLaying Anchors: Semantically Priming Numerals in Language Modeling
Mandar Sharma, Rutuja Taware, Pravesh Koirala, Nikhil Muralidhar, Naren Ramakrishnan. Findings of the Association for Computational Linguistics: NAACL 2024. 2024.
- Open Access
Learning Non-linguistic Skills without Sacrificing Linguistic Proficiency
The field of Math-NLP has witnessed significant growth in recent years, motivated by the desire to expand LLM performance to the learning of non-linguistic notions (numerals, and subsequently, arithmetic reasoning). However, non-linguistic skill injection typically comes at a cost for LLMs: it leads to catastrophic forgetting of core linguistic skills, a consequence that often remains unaddressed in the literature. As Math-NLP has been able to create LLMs that can closely approximate the mathematical skills of a grade-schooler or the arithmetic reasoning skills of a calculator, the practicality of these models fail if they concomitantly shed their linguistic capabilities. In this work, we take a closer look into the phenomena of catastrophic forgetting as it pertains to LLMs and subsequently offer a novel framework for non-linguistic skill injection for LLMs based on information theoretic interventions and skill-specific losses that enable the learning of strict arithmetic reasoning. Our model outperforms the state-of-the-art both on injected non-linguistic skills and on linguistic knowledge retention, and does so with a fraction of the non-linguistic training data (1/4) and zero additional synthetic linguistic training data.
Open AccessLearning Non-linguistic Skills without Sacrificing Linguistic Proficiency
The field of Math-NLP has witnessed significant growth in recent years, motivated by the desire to expand LLM performance to the learning of non-linguistic notions (numerals, and subsequently, arithmetic reasoning). However, non-linguistic skill injection typically comes at a cost for LLMs: it leads to catastrophic forgetting of core linguistic skills, a consequence that often remains unaddressed in the literature. As Math-NLP has been able to create LLMs that can closely approximate the mathematical skills of a grade-schooler or the arithmetic reasoning skills of a calculator, the practicality of these models fail if they concomitantly shed their linguistic capabilities. In this work, we take a closer look into the phenomena of catastrophic forgetting as it pertains to LLMs and subsequently offer a novel framework for non-linguistic skill injection for LLMs based on information theoretic interventions and skill-specific losses that enable the learning of strict arithmetic reasoning. Our model outperforms the state-of-the-art both on injected non-linguistic skills and on linguistic knowledge retention, and does so with a fraction of the non-linguistic training data (1/4) and zero additional synthetic linguistic training data.
- Open Access
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 6178-6191
Learning Non-linguistic Skills without Sacrificing Linguistic Proficiency
Mandar Sharma, Nikhil Muralidhar, Naren Ramakrishnan. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 6178-6191
Open AccessLearning Non-linguistic Skills without Sacrificing Linguistic Proficiency
Mandar Sharma, Nikhil Muralidhar, Naren Ramakrishnan. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.
- Open Access
Overcoming Barriers to Skill Injection in Language Modeling: Case Study in Arithmetic
Through their transfer learning abilities, highly-parameterized large pre-trained language models have dominated the NLP landscape for a multitude of downstream language tasks. Though linguistically proficient, the inability of these models to incorporate the learning of non-linguistic entities (numerals and arithmetic reasoning) limits their usage for tasks that require numeric comprehension or strict mathematical reasoning. However, as we illustrate in this paper, building a general purpose language model that also happens to be proficient in mathematical reasoning is not as straight-forward as training it on a numeric dataset. In this work, we develop a novel framework that enables language models to be mathematically proficient while retaining their linguistic prowess. Specifically, we offer information-theoretic interventions to overcome the catastrophic forgetting of linguistic skills that occurs while injecting non-linguistic skills into language models.
Open AccessOvercoming Barriers to Skill Injection in Language Modeling: Case Study in Arithmetic
Through their transfer learning abilities, highly-parameterized large pre-trained language models have dominated the NLP landscape for a multitude of downstream language tasks. Though linguistically proficient, the inability of these models to incorporate the learning of non-linguistic entities (numerals and arithmetic reasoning) limits their usage for tasks that require numeric comprehension or strict mathematical reasoning. However, as we illustrate in this paper, building a general purpose language model that also happens to be proficient in mathematical reasoning is not as straight-forward as training it on a numeric dataset. In this work, we develop a novel framework that enables language models to be mathematically proficient while retaining their linguistic prowess. Specifically, we offer information-theoretic interventions to overcome the catastrophic forgetting of linguistic skills that occurs while injecting non-linguistic skills into language models.
- 13 October 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 27 (2) , 1332-1342
Once Upon A Time In Visualization: Understanding the Use of Textual Narratives for Causality
Causality visualization can help people understand temporal chains of events, such as messages sent in a distributed system, cause and effect in a historical conflict, or the interplay between political actors over time. However, as the scale and complexity of these event sequences grows, even these visualizations can become overwhelming to use. In this paper, we propose the use of textual narratives as a data-driven storytelling method to augment causality visualization. We first propose a design space for how textual narratives can be used to describe causal data. We then present results from a crowdsourced user study where participants were asked to recover causality information from two causality visualizations—causal graphs and Hasse diagrams—with and without an associated textual narrative. Finally, we describe CAUSEWORKS, a causality visualization system for understanding how specific interventions influence a causal model. The system incorporates an automatic textual narrative mechanism based on our design space. We validate CAUSEWORKS through interviews with experts who used the system for understanding complex events.
- 13 October 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 27 (2) , 1332-1342
Once Upon A Time In Visualization: Understanding the Use of Textual Narratives for Causality
Causality visualization can help people understand temporal chains of events, such as messages sent in a distributed system, cause and effect in a historical conflict, or the interplay between political actors over time. However, as the scale and complexity of these event sequences grows, even these visualizations can become overwhelming to use. In this paper, we propose the use of textual narratives as a data-driven storytelling method to augment causality visualization. We first propose a design space for how textual narratives can be used to describe causal data. We then present results from a crowdsourced user study where participants were asked to recover causality information from two causality visualizations—causal graphs and Hasse diagrams—with and without an associated textual narrative. Finally, we describe CAUSEWORKS, a causality visualization system for understanding how specific interventions influence a causal model. The system incorporates an automatic textual narrative mechanism based on our design space. We validate CAUSEWORKS through interviews with experts who used the system for understanding complex events.