Sriram Balasubramanian

Vinu Sankar Sadasivan, Aounon Kumar, Sriram Balasubramanian et al. · harvard

Large Language Models (LLMs) perform impressively well in various applications. However, the potential for misuse of these models in activities such as plagiarism, generating fake news, and spamming has raised concern about their responsible use. Consequently, the reliable detection of AI-generated text has become a critical area of research. AI text detectors have shown to be effective under their specific settings. In this paper, we stress-test the robustness of these AI text detectors in the presence of an attacker. We introduce recursive paraphrasing attack to stress test a wide range of detection schemes, including the ones using the watermarking as well as neural network-based detectors, zero shot classifiers, and retrieval-based detectors. Our experiments conducted on passages, each approximately 300 tokens long, reveal the varying sensitivities of these detectors to our attacks. Our findings indicate that while our recursive paraphrasing method can significantly reduce detection rates, it only slightly degrades text quality in many cases, highlighting potential vulnerabilities in current detection systems in the presence of an attacker. Additionally, we investigate the susceptibility of watermarked LLMs to spoofing attacks aimed at misclassifying human-written text as AI-generated. We demonstrate that an attacker can infer hidden AI text signatures without white-box access to the detection method, potentially leading to reputational risks for LLM developers. Finally, we provide a theoretical framework connecting the AUROC of the best possible detector to the Total Variation distance between human and AI text distributions. This analysis offers insights into the fundamental challenges of reliable detection as language models continue to advance. Our code is publicly available at https://github.com/vinusankars/Reliability-of-AI-text-detectors.

Sriram Balasubramanian, Soheil Feizi

The ability to remove features from the input of machine learning models is very important to understand and interpret model predictions. However, this is non-trivial for vision models since masking out parts of the input image typically causes large distribution shifts. This is because the baseline color used for masking (typically grey or black) is out of distribution. Furthermore, the shape of the mask itself can contain unwanted signals which can be used by the model for its predictions. Recently, there has been some progress in mitigating this issue (called missingness bias) in image masking for vision transformers. In this work, we propose a new masking method for CNNs we call layer masking in which the missingness bias caused by masking is reduced to a large extent. Intuitively, layer masking applies a mask to intermediate activation maps so that the model only processes the unmasked input. We show that our method (i) is able to eliminate or minimize the influence of the mask shape or color on the output of the model, and (ii) is much better than replacing the masked region by black or grey for input perturbation based interpretability techniques like LIME. Thus, layer masking is much less affected by missingness bias than other masking strategies. We also demonstrate how the shape of the mask may leak information about the class, thus affecting estimates of model reliance on class-relevant features derived from input masking. Furthermore, we discuss the role of data augmentation techniques for tackling this problem, and argue that they are not sufficient for preventing model reliance on mask shape. The code for this project is publicly available at https://github.com/SriramB-98/layer_masking

Sriram Balasubramanian, Gaurang Sriramanan, Vinu Sankar Sadasivan et al.

Despite the remarkable success of deep neural networks in a myriad of settings, several works have demonstrated their overwhelming sensitivity to near-imperceptible perturbations, known as adversarial attacks. On the other hand, prior works have also observed that deep networks can be under-sensitive, wherein large-magnitude perturbations in input space do not induce appreciable changes to network activations. In this work, we study in detail the phenomenon of under-sensitivity in vision models such as CNNs and Transformers, and present techniques to study the geometry and extent of "equi-confidence" level sets of such networks. We propose a Level Set Traversal algorithm that iteratively explores regions of high confidence with respect to the input space using orthogonal components of the local gradients. Given a source image, we use this algorithm to identify inputs that lie in the same equi-confidence level set as the source image despite being perceptually similar to arbitrary images from other classes. We further observe that the source image is linearly connected by a high-confidence path to these inputs, uncovering a star-like structure for level sets of deep networks. Furthermore, we attempt to identify and estimate the extent of these connected higher-dimensional regions over which the model maintains a high degree of confidence. The code for this project is publicly available at https://github.com/SriramB-98/blindspots-neurips-sub

Kazem Faghih, Wenxiao Wang, Yize Cheng et al.

Large language models (LLMs) can now access a wide range of external tools, thanks to the Model Context Protocol (MCP). This greatly expands their abilities as various agents. However, LLMs rely entirely on the text descriptions of tools to decide which ones to use--a process that is surprisingly fragile. In this work, we expose a vulnerability in prevalent tool/function-calling protocols by investigating a series of edits to tool descriptions, some of which can drastically increase a tool's usage from LLMs when competing with alternatives. Through controlled experiments, we show that tools with properly edited descriptions receive over 10 times more usage from GPT-4.1 and Qwen2.5-7B than tools with original descriptions. We further evaluate how various edits to tool descriptions perform when competing directly with one another and how these trends generalize or differ across a broader set of 17 different models. These phenomena, while giving developers a powerful way to promote their tools, underscore the need for a more reliable foundation for agentic LLMs to select and utilize tools and resources. Our code is publicly available at https://github.com/kazemf78/llm-unreliable-tool-preferences.

Sriram Balasubramanian, Samyadeep Basu, Soheil Feizi

Recent work has explored how individual components of the CLIP-ViT model contribute to the final representation by leveraging the shared image-text representation space of CLIP. These components, such as attention heads and MLPs, have been shown to capture distinct image features like shape, color or texture. However, understanding the role of these components in arbitrary vision transformers (ViTs) is challenging. To this end, we introduce a general framework which can identify the roles of various components in ViTs beyond CLIP. Specifically, we (a) automate the decomposition of the final representation into contributions from different model components, and (b) linearly map these contributions to CLIP space to interpret them via text. Additionally, we introduce a novel scoring function to rank components by their importance with respect to specific features. Applying our framework to various ViT variants (e.g. DeiT, DINO, DINOv2, Swin, MaxViT), we gain insights into the roles of different components concerning particular image features. These insights facilitate applications such as image retrieval using text descriptions or reference images, visualizing token importance heatmaps, and mitigating spurious correlations. We release our code to reproduce the experiments at https://github.com/SriramB-98/vit-decompose

Zihao Lin, Samyadeep Basu, Mohammad Beigi et al.

The rise of foundation models has transformed machine learning research, prompting efforts to uncover their inner workings and develop more efficient and reliable applications for better control. While significant progress has been made in interpreting Large Language Models (LLMs), multimodal foundation models (MMFMs) - such as contrastive vision-language models, generative vision-language models, and text-to-image models - pose unique interpretability challenges beyond unimodal frameworks. Despite initial studies, a substantial gap remains between the interpretability of LLMs and MMFMs. This survey explores two key aspects: (1) the adaptation of LLM interpretability methods to multimodal models and (2) understanding the mechanistic differences between unimodal language models and crossmodal systems. By systematically reviewing current MMFM analysis techniques, we propose a structured taxonomy of interpretability methods, compare insights across unimodal and multimodal architectures, and highlight critical research gaps.

Mazda Moayeri, Samyadeep Basu, Sriram Balasubramanian et al.

Recent text-to-image generative models such as Stable Diffusion are extremely adept at mimicking and generating copyrighted content, raising concerns amongst artists that their unique styles may be improperly copied. Understanding how generative models copy "artistic style" is more complex than duplicating a single image, as style is comprised by a set of elements (or signature) that frequently co-occurs across a body of work, where each individual work may vary significantly. In our paper, we first reformulate the problem of "artistic copyright infringement" to a classification problem over image sets, instead of probing image-wise similarities. We then introduce ArtSavant, a practical (i.e., efficient and easy to understand) tool to (i) determine the unique style of an artist by comparing it to a reference dataset of works from 372 artists curated from WikiArt, and (ii) recognize if the identified style reappears in generated images. We leverage two complementary methods to perform artistic style classification over image sets, includingTagMatch, which is a novel inherently interpretable and attributable method, making it more suitable for broader use by non-technical stake holders (artists, lawyers, judges, etc). Leveraging ArtSavant, we then perform a large-scale empirical study to provide quantitative insight on the prevalence of artistic style copying across 3 popular text-to-image generative models. Namely, amongst a dataset of prolific artists (including many famous ones), only 20% of them appear to have their styles be at a risk of copying via simple prompting of today's popular text-to-image generative models.

Parsa Hosseini, Sumit Nawathe, Mazda Moayeri et al.

Unimodal vision models are known to rely on spurious correlations, but it remains unclear to what extent Multimodal Large Language Models (MLLMs) exhibit similar biases despite language supervision. In this paper, we investigate spurious bias in MLLMs and introduce SpurLens, a pipeline that leverages GPT-4 and open-set object detectors to automatically identify spurious visual cues without human supervision. Our findings reveal that spurious correlations cause two major failure modes in MLLMs: (1) over-reliance on spurious cues for object recognition, where removing these cues reduces accuracy, and (2) object hallucination, where spurious cues amplify the hallucination by over 10x. We validate our findings in various MLLMs and datasets. Beyond diagnosing these failures, we explore potential mitigation strategies, such as prompt ensembling and reasoning-based prompting, and conduct ablation studies to examine the root causes of spurious bias in MLLMs. By exposing the persistence of spurious correlations, our study calls for more rigorous evaluation methods and mitigation strategies to enhance the reliability of MLLMs.

Sriram Balasubramanian, Samyadeep Basu, Soheil Feizi

Chain-of-thought (CoT) reasoning enhances performance of large language models, but questions remain about whether these reasoning traces faithfully reflect the internal processes of the model. We present the first comprehensive study of CoT faithfulness in large vision-language models (LVLMs), investigating how both text-based and previously unexplored image-based biases affect reasoning and bias articulation. Our work introduces a novel, fine-grained evaluation pipeline for categorizing bias articulation patterns, enabling significantly more precise analysis of CoT reasoning than previous methods. This framework reveals critical distinctions in how models process and respond to different types of biases, providing new insights into LVLM CoT faithfulness. Our findings reveal that subtle image-based biases are rarely articulated compared to explicit text-based ones, even in models specialized for reasoning. Additionally, many models exhibit a previously unidentified phenomenon we term ``inconsistent'' reasoning - correctly reasoning before abruptly changing answers, serving as a potential canary for detecting biased reasoning from unfaithful CoTs. We then apply the same evaluation pipeline to revisit CoT faithfulness in LLMs across various levels of implicit cues. Our findings reveal that current language-only reasoning models continue to struggle with articulating cues that are not overtly stated.

Sriram Balasubramanian, Samyadeep Basu, Koustava Goswami et al.

Large language models (LLMs) are increasingly used for long-document question answering, where reliable attribution to sources is critical for trust. Existing post-hoc attribution methods work well for extractive QA but struggle in multi-hop, abstractive, and semi-extractive settings, where answers synthesize information across passages. To address these challenges, we argue that post-hoc attribution can be reframed as a reasoning problem, where answers are decomposed into constituent units, each tied to specific context. We first show that prompting models to generate such decompositions alongside attributions improves performance. Building on this, we introduce DecompTune, a post-training method that teaches models to produce answer decompositions as intermediate reasoning steps. We curate a diverse dataset of complex QA tasks, annotated with decompositions by a strong LLM, and post-train Qwen-2.5 (7B and 14B) using a two-stage SFT + GRPO pipeline with task-specific curated rewards. Across extensive experiments and ablations, DecompTune substantially improves attribution quality, outperforming prior methods and matching or exceeding state-of-the-art frontier models.

Anushka Yadav, Isha Nalawade, Srujana Pillarichety et al.

The emergence of reasoning models and their integration into practical AI chat bots has led to breakthroughs in solving advanced math, deep search, and extractive question answering problems that requires a complex and multi-step thought process. Yet, a complete understanding of why these models hallucinate more than general purpose language models is missing. In this investigative study, we systematicallyexplore reasoning failures of contemporary language models on multi-hop question answering tasks. We introduce a novel, nuanced error categorization framework that examines failures across three critical dimensions: the diversity and uniqueness of source documents involved ("hops"), completeness in capturing relevant information ("coverage"), and cognitive inefficiency ("overthinking"). Through rigorous hu-man annotation, supported by complementary automated metrics, our exploration uncovers intricate error patterns often hidden by accuracy-centric evaluations. This investigative approach provides deeper insights into the cognitive limitations of current models and offers actionable guidance toward enhancing reasoning fidelity, transparency, and robustness in future language modeling efforts.

Divyam Anshumaan, Sriram Balasubramanian, Shubham Tiwari et al.

Simulating physical network paths (e.g., Internet) is a cornerstone research problem in the emerging sub-field of AI-for-networking. We seek a model that generates end-to-end packet delay values in response to the time-varying load offered by a sender, which is typically a function of the previously output delays. The problem setting is unique, and renders the state-of-the-art text and time-series generative models inapplicable or ineffective. We formulate an ML problem at the intersection of dynamical systems, sequential decision making, and time-series modeling. We propose a novel grey-box approach to network simulation that embeds the semantics of physical network path in a new RNN-style model called RBU, providing the interpretability of standard network simulator tools, the power of neural models, the efficiency of SGD-based techniques for learning, and yielding promising results on synthetic and real-world network traces.

Sriram Balasubramanian, Naman Jain, Gaurav Jindal et al.

We evaluate named entity representations of BERT-based NLP models by investigating their robustness to replacements from the same typed class in the input. We highlight that on several tasks while such perturbations are natural, state of the art trained models are surprisingly brittle. The brittleness continues even with the recent entity-aware BERT models. We also try to discern the cause of this non-robustness, considering factors such as tokenization and frequency of occurrence. Then we provide a simple method that ensembles predictions from multiple replacements while jointly modeling the uncertainty of type annotations and label predictions. Experiments on three NLP tasks show that our method enhances robustness and increases accuracy on both natural and adversarial datasets.