Naren Ramakrishnan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Naren Ramakrishnan has a total of 356 co-authors. Here are the top co-authors by number of shared publications:
- Chang-Tien Lu
Virginia Tech, Alexandria, USA
8 shared publications - Mandar Sharma
Virginia Tech Virginia USA
7 shared publications - Feng Chen
Department of Computer Science University at Albany SUNY Albany NY USA
5 shared publications - Nikhil Muralidhar
Department of Computer Science Stevens Institute of Technology Hoboken NJ USA
5 shared publications - Shengzhe Xu
Virginia Tech
5 shared publications - David R. Mares
University of California at San Diego San Diego CA USA
4 shared publications
Latest Publications
- Open Access
- 11 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 94-100
Demystify, Use, Reflect, Assess (DURA): An Experience Report on LLM Integration in CS2
- 11 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 94-100
Open AccessDemystify, Use, Reflect, Assess (DURA): An Experience Report on LLM Integration in CS2
- Open Access
- 26 October 2026
- Published by MDPI AG in Preprints.org
Mechanistic Interpretability of LLM Behavior: A Survey
Mechanistic interpretability seeks to explain how internal computations produce large language model behaviors, yet findings remain fragmented across methods and behavioral domains. We survey 229 papers across five behavior families: epistemic, linguistic, reasoning, safety, and social behaviors. We introduce a framework distinguishing five levels of mechanistic evidence, from decodability to generalization. Our cross-behavior synthesis reveals recurring mechanisms, distinctions between representation and causal control, and limitations of existing explanations. We conclude by identifying gaps in understanding computational roles, behavioral interactions, and generalization to interactive and agentic settings.
- 26 October 2026
- Published by MDPI AG in Preprints.org
Open AccessMechanistic Interpretability of LLM Behavior: A Survey
Mechanistic interpretability seeks to explain how internal computations produce large language model behaviors, yet findings remain fragmented across methods and behavioral domains. We survey 229 papers across five behavior families: epistemic, linguistic, reasoning, safety, and social behaviors. We introduce a framework distinguishing five levels of mechanistic evidence, from decodability to generalization. Our cross-behavior synthesis reveals recurring mechanisms, distinctions between representation and causal control, and limitations of existing explanations. We conclude by identifying gaps in understanding computational roles, behavioral interactions, and generalization to interactive and agentic settings.
- Open Access
Multi-season evaluation and analysis of categorical trend forecasts of influenza hospital admissions in the United States
Forecasting influenza hospitalizations informs public health preparedness, yet questions remain about which types of forecasts best guide action. We evaluate categorical trend forecasts, which communicate probabilities of upcoming increases or decreases in epidemic trajectories, submitted to CDC’s FluSight Forecasting Challenge between Fall-2024 and Spring-2026. Teams submitted probability distributions over five categories describing direction and magnitude of week-over-week changes in laboratory-confirmed influenza hospital admissions. We assessed performance using Ranked Probability Skill Score, Brier Skill Score, and measures of forecast-observation agreement. Most models outperformed an equal-probability baseline; the FluSight ensemble ranked among the top three in the 2024–25 and 2025–26 seasons. Forecasts were most accurate during stable periods and least during periods of rapid change, with most models underestimating observed trends. Conclusions were robust to choice of scoring metric and reference model. These results support categorical trend ensembles as an approach to communicating infectious disease forecasts that may inform public health decision-making.
Open AccessMulti-season evaluation and analysis of categorical trend forecasts of influenza hospital admissions in the United States
Forecasting influenza hospitalizations informs public health preparedness, yet questions remain about which types of forecasts best guide action. We evaluate categorical trend forecasts, which communicate probabilities of upcoming increases or decreases in epidemic trajectories, submitted to CDC’s FluSight Forecasting Challenge between Fall-2024 and Spring-2026. Teams submitted probability distributions over five categories describing direction and magnitude of week-over-week changes in laboratory-confirmed influenza hospital admissions. We assessed performance using Ranked Probability Skill Score, Brier Skill Score, and measures of forecast-observation agreement. Most models outperformed an equal-probability baseline; the FluSight ensemble ranked among the top three in the 2024–25 and 2025–26 seasons. Forecasts were most accurate during stable periods and least during periods of rapid change, with most models underestimating observed trends. Conclusions were robust to choice of scoring metric and reference model. These results support categorical trend ensembles as an approach to communicating infectious disease forecasts that may inform public health decision-making.
- Open Access
- 4 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 625-644
Noise, Why Can't You Bend? Detecting Adversarial Perturbations in Wireless Sensing via Structural Fragility
- 4 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 625-644
Open AccessNoise, Why Can't You Bend? Detecting Adversarial Perturbations in Wireless Sensing via Structural Fragility
- 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
Modeling Epidemiological Dynamics Under Adversarial Data and User Deception
Epidemiological models increasingly rely on self-reported behavioral data such as vaccination status, mask usage, and social distancing adherence to forecast disease transmission and assess the impact of non-pharmaceutical interventions (NPIs). While such data provide valuable real-time insights, they are often subject to strategic misreporting, driven by individual incentives to avoid penalties, access benefits, or express distrust in public health authorities. To account for such human behavior, in this paper, we introduce a game-theoretic framework that models the interaction between the population and a public health authority as a signaling game. Individuals (senders) choose how to report their behaviors, while the public health authority (receiver) updates their epidemiological model(s) based on potentially distorted signals. Focusing on deception around masking and vaccination, we characterize analytically game equilibrium outcomes and evaluate the degree to which deception can be tolerated while maintaining epidemic control through policy interventions. Our results show that separating equilibria-with minimal deception-drive infections to near zero over time. Remarkably, even under pervasive dishonesty in pooling equilibria, well-designed sender and receiver strategies can still maintain effective epidemic control. This work advances the understanding of adversarial data in epidemiology and offers tools for designing more robust public health models in the presence of strategic user behavior.
Open AccessModeling Epidemiological Dynamics Under Adversarial Data and User Deception
Epidemiological models increasingly rely on self-reported behavioral data such as vaccination status, mask usage, and social distancing adherence to forecast disease transmission and assess the impact of non-pharmaceutical interventions (NPIs). While such data provide valuable real-time insights, they are often subject to strategic misreporting, driven by individual incentives to avoid penalties, access benefits, or express distrust in public health authorities. To account for such human behavior, in this paper, we introduce a game-theoretic framework that models the interaction between the population and a public health authority as a signaling game. Individuals (senders) choose how to report their behaviors, while the public health authority (receiver) updates their epidemiological model(s) based on potentially distorted signals. Focusing on deception around masking and vaccination, we characterize analytically game equilibrium outcomes and evaluate the degree to which deception can be tolerated while maintaining epidemic control through policy interventions. Our results show that separating equilibria-with minimal deception-drive infections to near zero over time. Remarkably, even under pervasive dishonesty in pooling equilibria, well-designed sender and receiver strategies can still maintain effective epidemic control. This work advances the understanding of adversarial data in epidemiology and offers tools for designing more robust public health models in the presence of strategic user behavior.
- Open Access
- 17 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 1299-1300
Demystify, Use, Reflect: Preparing students to be informed LLM-users
- 17 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 1299-1300
Open AccessDemystify, Use, Reflect: Preparing students to be informed LLM-users
- Open Access
How (Not) to Hybridize Neural and Mechanistic Models for Epidemiological Forecasting
Epidemiological forecasting from surveillance data is a hard problem and hybridizing mechanistic compartmental models with neural models is a natural direction. The mechanistic structure helps keep trajectories epidemiologically plausible, while neural components can capture non-stationary, data-adaptive effects. In practice, however, many seemingly straightforward couplings fail under partial observability and continually shifting transmission dynamics driven by behavior, waning immunity, seasonality, and interventions. We catalog these failure modes and show that robust performance requires making non-stationarity explicit: we extract multi-scale structure from the observed infection series and use it as an interpretable control signal for a controlled neural ODE coupled to an epidemiological model. Concretely, we decompose infections into trend, seasonal, and residual components and use these signals to drive continuous-time latent dynamics while jointly forecasting and inferring time-varying transmission, recovery, and immunity-loss rates. Across seasonal and non-seasonal settings, including early outbreaks and multi-wave regimes, our approach reduces long-horizon RMSE by 15-35%, improves peak timing error by 1-3 weeks, and lowers peak magnitude bias by up to 30% relative to strong time-series, neural ODE, and hybrid baselines, without relying on auxiliary covariates.
Open AccessHow (Not) to Hybridize Neural and Mechanistic Models for Epidemiological Forecasting
Epidemiological forecasting from surveillance data is a hard problem and hybridizing mechanistic compartmental models with neural models is a natural direction. The mechanistic structure helps keep trajectories epidemiologically plausible, while neural components can capture non-stationary, data-adaptive effects. In practice, however, many seemingly straightforward couplings fail under partial observability and continually shifting transmission dynamics driven by behavior, waning immunity, seasonality, and interventions. We catalog these failure modes and show that robust performance requires making non-stationarity explicit: we extract multi-scale structure from the observed infection series and use it as an interpretable control signal for a controlled neural ODE coupled to an epidemiological model. Concretely, we decompose infections into trend, seasonal, and residual components and use these signals to drive continuous-time latent dynamics while jointly forecasting and inferring time-varying transmission, recovery, and immunity-loss rates. Across seasonal and non-seasonal settings, including early outbreaks and multi-wave regimes, our approach reduces long-horizon RMSE by 15-35%, improves peak timing error by 1-3 weeks, and lowers peak magnitude bias by up to 30% relative to strong time-series, neural ODE, and hybrid baselines, without relying on auxiliary covariates.
- 13 October 2025
- Published by Springer Nature
- p. 366-387
Let the Noise Speak: Harnessing Noise for a Unified Defense Against Adversarial and Backdoor Attacks
- 13 October 2025
- Published by Springer Nature
- p. 366-387
Let the Noise Speak: Harnessing Noise for a Unified Defense Against Adversarial and Backdoor Attacks
- Open Access
Can an LLM Induce a Graph? Investigating Memory Drift and Context Length
Recently proposed evaluation benchmarks aim to characterize the effective context length and the forgetting tendencies of large language models (LLMs). However, these benchmarks often rely on simplistic 'needle in a haystack' retrieval or continuation tasks that may not accurately reflect the performance of these models in information-dense scenarios. Thus, rather than simple next token prediction, we argue for evaluating these models on more complex reasoning tasks that requires them to induce structured relational knowledge from the text - such as graphs from potentially noisy natural language content. While the input text can be viewed as generated in terms of a graph, its structure is not made explicit and connections must be induced from distributed textual cues, separated by long contexts and interspersed with irrelevant information. Our findings reveal that LLMs begin to exhibit memory drift and contextual forgetting at much shorter effective lengths when tasked with this form of relational reasoning, compared to what existing benchmarks suggest. With these findings, we offer recommendations for the optimal use of popular LLMs for complex reasoning tasks. We further show that even models specialized for reasoning, such as OpenAI o1, remain vulnerable to early memory drift in these settings. These results point to significant limitations in the models' ability to abstract structured knowledge from unstructured input and highlight the need for architectural adaptations to improve long-range reasoning.
Open AccessCan an LLM Induce a Graph? Investigating Memory Drift and Context Length
Recently proposed evaluation benchmarks aim to characterize the effective context length and the forgetting tendencies of large language models (LLMs). However, these benchmarks often rely on simplistic 'needle in a haystack' retrieval or continuation tasks that may not accurately reflect the performance of these models in information-dense scenarios. Thus, rather than simple next token prediction, we argue for evaluating these models on more complex reasoning tasks that requires them to induce structured relational knowledge from the text - such as graphs from potentially noisy natural language content. While the input text can be viewed as generated in terms of a graph, its structure is not made explicit and connections must be induced from distributed textual cues, separated by long contexts and interspersed with irrelevant information. Our findings reveal that LLMs begin to exhibit memory drift and contextual forgetting at much shorter effective lengths when tasked with this form of relational reasoning, compared to what existing benchmarks suggest. With these findings, we offer recommendations for the optimal use of popular LLMs for complex reasoning tasks. We further show that even models specialized for reasoning, such as OpenAI o1, remain vulnerable to early memory drift in these settings. These results point to significant limitations in the models' ability to abstract structured knowledge from unstructured input and highlight the need for architectural adaptations to improve long-range reasoning.