Palash Goyal

Mihir Parmar, Palash Goyal, Xin Liu et al.

Recently, decomposing complex problems into simple subtasks--a crucial part of human-like natural planning--to solve the given problem has significantly boosted the performance of large language models (LLMs). However, leveraging such planning structures during post-training to boost the performance of smaller open-source LLMs remains underexplored. Motivated by this, we introduce PLAN-TUNING, a unified post-training framework that (i) distills synthetic task decompositions (termed "planning trajectories") from large-scale LLMs and (ii) fine-tunes smaller models via supervised and reinforcement-learning objectives designed to mimic these planning processes to improve complex reasoning. On GSM8k and the MATH benchmarks, plan-tuned models outperform strong baselines by an average $\sim7\%$. Furthermore, plan-tuned models show better generalization capabilities on out-of-domain datasets, with average $\sim10\%$ and $\sim12\%$ performance improvements on OlympiadBench and AIME 2024, respectively. Our detailed analysis demonstrates how planning trajectories improves complex reasoning capabilities, showing that PLAN-TUNING is an effective strategy for improving task-specific performance of smaller LLMs.

Ninareh Mehrabi, Palash Goyal, Christophe Dupuy et al. · amazon-science

Warning: this paper contains content that may be inappropriate or offensive. As generative models become available for public use in various applications, testing and analyzing vulnerabilities of these models has become a priority. In this work, we propose an automatic red teaming framework that evaluates a given black-box model and exposes its vulnerabilities against unsafe and inappropriate content generation. Our framework uses in-context learning in a feedback loop to red team models and trigger them into unsafe content generation. In particular, taking text-to-image models as target models, we explore different feedback mechanisms to automatically learn effective and diverse adversarial prompts. Our experiments demonstrate that even with enhanced safety features, Stable Diffusion (SD) models are vulnerable to our adversarial prompts, raising concerns on their robustness in practical uses. Furthermore, we demonstrate that the proposed framework is effective for red teaming text-to-text models.

Junyi Li, Ninareh Mehrabi, Charith Peris et al. · amazon-science

Large language models (LLMs) are known to generate biased responses where the opinions of certain groups and populations are underrepresented. Here, we present a novel approach to achieve controllable generation of specific viewpoints using LLMs, that can be leveraged to produce multiple perspectives and to reflect the diverse opinions. Moving beyond the traditional reliance on demographics like age, gender, or party affiliation, we introduce a data-driven notion of persona grounded in collaborative filtering, which is defined as either a single individual or a cohort of individuals manifesting similar views across specific inquiries. As individuals in the same demographic group may have different personas, our data-driven persona definition allows for a more nuanced understanding of different (latent) social groups present in the population. In addition to this, we also explore an efficient method to steer LLMs toward the personas that we define. We show that our data-driven personas significantly enhance model steerability, with improvements of between $57\%-77\%$ over our best performing baselines.

Ninareh Mehrabi, Palash Goyal, Apurv Verma et al. · amazon-science, gatech

Natural language often contains ambiguities that can lead to misinterpretation and miscommunication. While humans can handle ambiguities effectively by asking clarifying questions and/or relying on contextual cues and common-sense knowledge, resolving ambiguities can be notoriously hard for machines. In this work, we study ambiguities that arise in text-to-image generative models. We curate a benchmark dataset covering different types of ambiguities that occur in these systems. We then propose a framework to mitigate ambiguities in the prompts given to the systems by soliciting clarifications from the user. Through automatic and human evaluations, we show the effectiveness of our framework in generating more faithful images aligned with human intention in the presence of ambiguities.

Ninareh Mehrabi, Palash Goyal, Anil Ramakrishna et al. · amazon-science

With the recent surge of language models in different applications, attention to safety and robustness of these models has gained significant importance. Here we introduce a joint framework in which we simultaneously probe and improve the robustness of a black-box target model via adversarial prompting and belief augmentation using iterative feedback loops. This framework utilizes an automated red teaming approach to probe the target model, along with a belief augmenter to generate instructions for the target model to improve its robustness to those adversarial probes. Importantly, the adversarial model and the belief generator leverage the feedback from past interactions to improve the effectiveness of the adversarial prompts and beliefs, respectively. In our experiments, we demonstrate that such a framework can reduce toxic content generation both in dynamic cases where an adversary directly interacts with a target model and static cases where we use a static benchmark dataset to evaluate our model.

Rui Meng, Bhavana Dalvi Mishra, Jiefeng Chen et al.

Autonomous research agents produce competitive solutions and professional-looking manuscripts, yet their outputs contain verifiability failures undetectable by surface-level evaluation: fabricated citations, unreproducible scores, and method descriptions that diverge from the implementation. We address this through three contributions. First, Chain-of-Evidence (CoE), a verifiability framework requiring every claim to be traceable to its evidence source. Second, ScientistOne, an end-to-end autonomous research system that maintains evidence chains by construction throughout literature review, solution discovery, and paper writing. Third, CoE Audit, a post-hoc audit whose four integrity checks -- score verification, specification violation, reference verification, and method-code alignment -- apply uniformly to all systems. Across 75 papers spanning five systems and five frontier research tasks, every baseline exhibits at least one systematic failure mode: hallucinated reference rates reach 21%, score verification passes in as few as 42% of papers, and method-code alignment ranges from 20% to 80%. ScientistOne achieves zero hallucinated references (0/337), perfect score verification (12/12), and the highest method-code alignment (14/15), while matching or exceeding human expert performance on all five tasks. ScientistOne further generalizes to six additional tasks spanning medical imaging, fine-grained recognition, 3D perception, and language modeling, achieving state-of-the-art on Parameter Golf and gold medals on MLE-Bench tasks where baselines fail entirely.

Md Atik Ahamed, Mihir Parmar, Palash Goyal et al.

We introduce TFRBench, the first benchmark designed to evaluate the reasoning capabilities of forecasting systems. Traditionally, time-series forecasting has been evaluated solely on numerical accuracy, treating foundation models as ``black boxes.'' Unlike existing benchmarks, TFRBench provides a protocol for evaluating the reasoning generated by forecasting systems--specifically their analysis of cross-channel dependencies, trends, and external events. To enable this, we propose a systematic multi-agent framework that utilizes an iterative verification loop to synthesize numerically grounded reasoning traces. Spanning ten datasets across five domains, our evaluation confirms that this reasoning is causally effective; useful for evaluation; and prompting LLMs with our generated traces significantly improves forecasting accuracy compared to direct numerical prediction (e.g., avg. $\sim40.2\%\to56.6\%)$, validating the quality of our reasoning. Conversely, benchmarking experiments reveal that off-the-shelf LLMs consistently struggle with both reasoning (lower LLM-as-a-Judge scores) and numerical forecasting, frequently failing to capture domain-specific dynamics. TFRBench thus establishes a new standard for interpretable, reasoning-based evaluation in time-series forecasting. Our benchmark is available at: https://tfrbench.github.io

Palash Goyal, Mihir Parmar, Yiwen Song et al.

Automated peer review has evolved from simple text classification to structured feedback generation. However, current state-of-the-art systems still struggle with "surface-level" critiques: they excel at summarizing content but often fail to accurately assess novelty and significance or identify deep methodological flaws because they evaluate papers in a vacuum, lacking the external context a human expert possesses. In this paper, we introduce ScholarPeer, a search-enabled multi-agent framework designed to emulate the cognitive processes of a senior researcher. ScholarPeer employs a dual-stream process of context acquisition and active verification. It dynamically constructs a domain narrative using a historian agent, identifies missing comparisons via a baseline scout, and verifies claims through a multi-aspect Q&A engine, grounding the critique in live web-scale literature. We evaluate ScholarPeer on DeepReview-13K and the results demonstrate that ScholarPeer achieves significant win-rates against state-of-the-art approaches in side-by-side evaluations and reduces the gap to human-level diversity.

Ishani Mondal, Yiwen Song, Mihir Parmar et al.

Long-form visual storytelling requires maintaining continuity across shots, including consistent characters, stable environments, and smooth scene transitions. While existing generative models can produce strong individual frames, they fail to preserve such continuity, leading to appearance changes, inconsistent backgrounds, and abrupt scene shifts. We introduce CANVAS (Continuity-Aware Narratives via Visual Agentic Storyboarding), a multi-agent framework that explicitly plans visual continuity in multi-shot narratives. CANVAS enforces coherence through character continuity, persistent background anchors, and location-aware scene planning for smooth transitions within the same setting We evaluate CANVAS on two storyboard generation benchmarks ST-BENCH and ViStoryBench and introduce a new challenging benchmark HardContinuityBench for long-range narrative consistency. CANVAS consistently outperforms the best-performing baseline, improving background continuity by 21.6%, character consistency by 9.6% and props consistency by 7.6%.

Sarkar Snigdha Sarathi Das, Palash Goyal, Mihir Parmar et al.

Pre-trained Time Series Foundational Models (TSFMs) represent a significant advance, capable of forecasting diverse time series with complex characteristics, including varied seasonalities, trends, and long-range dependencies. Despite their primary goal of universal time series forecasting, their efficacy is far from uniform; divergent training protocols and data sources cause individual TSFMs to exhibit highly variable performance across different forecasting tasks, domains, and horizons. Leveraging this complementary expertise by arbitrating existing TSFM outputs presents a compelling strategy, yet this remains a largely unexplored area of research. In this paper, we conduct a thorough examination of how different TSFMs exhibit specialized performance profiles across various forecasting settings, and how we can effectively leverage this behavior in arbitration between different time series models. We specifically analyze how factors such as model selection and forecast horizon distribution can influence the efficacy of arbitration strategies. Based on this analysis, we propose Synapse, a novel arbitration framework for TSFMs. Synapse is designed to dynamically leverage a pool of TSFMs, assign and adjust predictive weights based on their relative, context-dependent performance, and construct a robust forecast distribution by adaptively sampling from the output quantiles of constituent models. Experimental results demonstrate that Synapse consistently outperforms other popular ensembling techniques as well as individual TSFMs, demonstrating Synapse's efficacy in time series forecasting.

Alireza Salemi, Mihir Parmar, Palash Goyal et al.

The rapid advancement of Large Language Models (LLMs) has opened new opportunities in data science, yet their practical deployment is often constrained by the challenge of discovering relevant data within large heterogeneous data lakes. Existing methods struggle with this: single-agent systems are quickly overwhelmed by large, heterogeneous files in the large data lakes, while multi-agent systems designed based on a master-slave paradigm depend on a rigid central controller for task allocation that requires precise knowledge of each sub-agent's capabilities. To address these limitations, we propose a novel multi-agent communication paradigm inspired by the blackboard architecture for traditional AI models. In this framework, a central agent posts requests to a shared blackboard, and autonomous subordinate agents -- either responsible for a partition of the data lake or general information retrieval -- volunteer to respond based on their capabilities. This design improves scalability and flexibility by eliminating the need for a central coordinator to have prior knowledge of all sub-agents' expertise. We evaluate our method on three benchmarks that require explicit data discovery: KramaBench and modified versions of DS-Bench and DA-Code to incorporate data discovery. Experimental results demonstrate that the blackboard architecture substantially outperforms baselines, including RAG and the master-slave multi-agent paradigm, achieving between 13% to 57% relative improvement in end-to-end task success and up to a 9% relative gain in F1 score for data discovery over the best-performing baselines across both proprietary and open-source LLMs. Our findings establish the blackboard paradigm as a scalable and generalizable communication framework for multi-agent systems.

Sarkar Snigdha Sarathi Das, Palash Goyal, Mihir Parmar et al.

Time series forecasting is not just numerical extrapolation, but often requires reasoning with unstructured contextual data such as news or events. While specialized Time Series Foundation Models (TSFMs) excel at forecasting based on numerical patterns, they remain unaware to real-world textual signals. Conversely, while LLMs are emerging as zero-shot forecasters, their performance remains uneven across domains and contextual grounding. To bridge this gap, we introduce Nexus, a multi-agent forecasting framework that decomposes prediction into specialized stages: isolating macro-level and micro-level temporal fluctuations, and integrating contextual information when available before synthesizing a final forecast. This decomposition enables Nexus to adapt from seasonal signals to volatile, event-driven information without relying on external statistical anchors or monolithic prompting. We show that current-generation LLMs possess substantially stronger intrinsic forecasting ability than previously recognized, depending critically on how numerical and contextual reasoning are organized. Evaluated on data strictly succeeding LLM knowledge cutoffs spanning Zillow real estate metrics and volatile stock market equities, Nexus consistently matches or outperforms state-of-the-art TSFMs and strong LLM baselines. Beyond numerical accuracy, Nexus produces high-quality reasoning traces that explicitly show the fundamental drivers behind each forecast. Our results establish that real-world forecasting is an agentic reasoning problem extending well beyond only sequence modeling.

Chan Hee Song, Yiwen Song, Palash Goyal et al. · microsoft-research

Computer use agents (CUAs) need to plan task workflows grounded in diverse, ever-changing applications and environments, but learning is hindered by the scarcity of large-scale, high-quality training data in the target application. Existing datasets are domain-specific, static, and costly to annotate, while current synthetic data generation methods often yield simplistic or misaligned task demonstrations. To address these limitations, we introduce Watch & Learn (W&L), a framework that converts human demonstration videos readily available on the Internet into executable UI trajectories at scale. Instead of directly generating trajectories or relying on ad hoc reasoning heuristics, we cast the problem as an inverse dynamics objective: predicting the user's action from consecutive screen states. This formulation reduces manual engineering, is easier to learn, and generalizes more robustly across applications. Concretely, we develop an inverse dynamics labeling pipeline with task-aware video retrieval, generate over 53k high-quality trajectories from raw web videos, and demonstrate that these trajectories improve CUAs both as in-context demonstrations and as supervised training data. On the challenging OSWorld benchmark, UI trajectories extracted with W&L consistently enhance both general-purpose and state-of-the-art frameworks in-context, and deliver stronger gains for open-source models under supervised training. These results highlight web-scale human demonstration videos as a practical and scalable foundation for advancing CUAs towards real-world deployment.

Palash Goyal, Di Huang, Ankita Goswami et al.

Graph embedding is the task of representing nodes of a graph in a low-dimensional space and its applications for graph tasks have gained significant traction in academia and industry. The primary difference among the many recently proposed graph embedding methods is the way they preserve the inherent properties of the graphs. However, in practice, comparing these methods is very challenging. The majority of methods report performance boosts on few selected real graphs. Therefore, it is difficult to generalize these performance improvements to other types of graphs. Given a graph, it is currently impossible to quantify the advantages of one approach over another. In this work, we introduce a principled framework to compare graph embedding methods. Our goal is threefold: (i) provide a unifying framework for comparing the performance of various graph embedding methods, (ii) establish a benchmark with real-world graphs that exhibit different structural properties, and (iii) provide users with a tool to identify the best graph embedding method for their data. This paper evaluates 4 of the most influential graph embedding methods and 4 traditional link prediction methods against a corpus of 100 real-world networks with varying properties. We organize the 100 networks in terms of their properties to get a better understanding of the embedding performance of these popular methods. We use the comparisons on our 100 benchmark graphs to define GFS-score, that can be applied to any embedding method to quantify its performance. We rank the state-of-the-art embedding approaches using the GFS-score and show that it can be used to understand and evaluate novel embedding approaches. We envision that the proposed framework (https://www.github.com/palash1992/GEM-Benchmark) will serve the community as a benchmarking platform to test and compare the performance of future graph embedding techniques.

Shih Yuan Yu, Sujit Rokka Chhetri, Arquimedes Canedo et al.

Pykg2vec is an open-source Python library for learning the representations of the entities and relations in knowledge graphs. Pykg2vec's flexible and modular software architecture currently implements 16 state-of-the-art knowledge graph embedding algorithms, and is designed to easily incorporate new algorithms. The goal of pykg2vec is to provide a practical and educational platform to accelerate research in knowledge graph representation learning. Pykg2vec is built on top of TensorFlow and Python's multiprocessing framework and provides modules for batch generation, Bayesian hyperparameter optimization, mean rank evaluation, embedding, and result visualization. Pykg2vec is released under the MIT License and is also available in the Python Package Index (PyPI). The source code of pykg2vec is available at https://github.com/Sujit-O/pykg2vec.

Palash Goyal, Sujit Rokka Chhetri, Ninareh Mehrabi et al.

DynamicGEM is an open-source Python library for learning node representations of dynamic graphs. It consists of state-of-the-art algorithms for defining embeddings of nodes whose connections evolve over time. The library also contains the evaluation framework for four downstream tasks on the network: graph reconstruction, static and temporal link prediction, node classification, and temporal visualization. We have implemented various metrics to evaluate the state-of-the-art methods, and examples of evolving networks from various domains. We have easy-to-use functions to call and evaluate the methods and have extensive usage documentation. Furthermore, DynamicGEM provides a template to add new algorithms with ease to facilitate further research on the topic.

Palash Goyal, Emilio Ferrara

Graphs, such as social networks, word co-occurrence networks, and communication networks, occur naturally in various real-world applications. Analyzing them yields insight into the structure of society, language, and different patterns of communication. Many approaches have been proposed to perform the analysis. Recently, methods which use the representation of graph nodes in vector space have gained traction from the research community. In this survey, we provide a comprehensive and structured analysis of various graph embedding techniques proposed in the literature. We first introduce the embedding task and its challenges such as scalability, choice of dimensionality, and features to be preserved, and their possible solutions. We then present three categories of approaches based on factorization methods, random walks, and deep learning, with examples of representative algorithms in each category and analysis of their performance on various tasks. We evaluate these state-of-the-art methods on a few common datasets and compare their performance against one another. Our analysis concludes by suggesting some potential applications and future directions. We finally present the open-source Python library we developed, named GEM (Graph Embedding Methods, available at https://github.com/palash1992/GEM), which provides all presented algorithms within a unified interface to foster and facilitate research on the topic.

Md Atik Ahamed, Mihir Parmar, Palash Goyal et al.

Time Series Foundation Models (TSFMs) excel at numerical forecasting but operate as black boxes lacking qualitative reasoning. Conversely, applying LLMs directly to temporal data introduces a modality gap: text tokenizers fragment continuous numerical values, degrading mathematical relationships and exploding sequence lengths, leading to computational overhead. To resolve this, we introduce STRIDE (Strategic Time-series Reasoning Injected via Distilled Embeddings), a novel framework natively integrating LLM reasoning into the continuous embedding space of TSFMs. Instead of discrete tokens, STRIDE distills reasoning traces into a lightweight LLM, dynamically projecting its mean-pooled hidden states as a cross-modal prior into the target numerical encoder. The architecture is jointly optimized using cross-entropy and quantile losses. Evaluations demonstrate STRIDE establishes state-of-the-art numerical forecasting on GIFT-Eval (0.674 MASE, 0.454 CRPS) compared to TSFMs and exhibits superior in-domain and out-of-domain numerical as well as reasoning performance on TFRBench. Specifically, STRIDE acts as a plug-and-play enhancement, consistently improving diverse TSFMs (e.g., Chronos-2, Timer-S1) across various LLM configurations. Thus, injecting semantic reasoning as a continuous prior equips TSFMs with human-interpretable reasoning while fundamentally improving predictive accuracy.

Mingtian Tan, Mihir Parmar, Palash Goyal et al.

Large Language Models (LLMs) are increasingly applied to forecasting. To evaluate this capability while mitigating pre-training data contamination, several living benchmarks have been proposed. However, existing benchmarks either lack the multidimensional events essential for accurate forecasting due to data scarcity, or focus on relatively closed environments. To assess the predictive capabilities of LLMs in complex, real-world scenarios, we propose LEAF, the first living benchmark for event-augmented forecasting tasks, including future event probabilities, trend and time series forecasting. LEAF utilizes a recursive retrieval agent system paired with dual-agent cross-validation to provide comprehensive and relevant auxiliary text for forecasting. Evaluating state-of-the-art proprietary and open-weight LLMs, we find that these models can leverage signals extracted from complex events to enhance predictive performance. In the stock domain, we find that LLMs achieve better performance on equities they confidently identify as more predictable. Furthermore, the events demonstrate a strong correlation with the target equities. To this end, LEAF provides a necessary, dynamically updating testbed to continuously track and drive progress in event-driven forecasting tasks.

Anaelia Ovalle, Ninareh Mehrabi, Palash Goyal et al. · amazon-science

Gender-inclusive NLP research has documented the harmful limitations of gender binary-centric large language models (LLM), such as the inability to correctly use gender-diverse English neopronouns (e.g., xe, zir, fae). While data scarcity is a known culprit, the precise mechanisms through which scarcity affects this behavior remain underexplored. We discover LLM misgendering is significantly influenced by Byte-Pair Encoding (BPE) tokenization, the tokenizer powering many popular LLMs. Unlike binary pronouns, BPE overfragments neopronouns, a direct consequence of data scarcity during tokenizer training. This disparate tokenization mirrors tokenizer limitations observed in multilingual and low-resource NLP, unlocking new misgendering mitigation strategies. We propose two techniques: (1) pronoun tokenization parity, a method to enforce consistent tokenization across gendered pronouns, and (2) utilizing pre-existing LLM pronoun knowledge to improve neopronoun proficiency. Our proposed methods outperform finetuning with standard BPE, improving neopronoun accuracy from 14.1% to 58.4%. Our paper is the first to link LLM misgendering to tokenization and deficient neopronoun grammar, indicating that LLMs unable to correctly treat neopronouns as pronouns are more prone to misgender.

Mihir Parmar, Xin Liu, Palash Goyal et al.

Recent agent frameworks and inference-time algorithms often struggle with complex planning problems due to limitations in verifying generated plans or reasoning and varying complexity of instances within a single task. Many existing methods for these tasks either perform task-level verification without considering constraints or apply inference-time algorithms without adapting to instance-level complexity. To address these limitations, we propose PlanGEN, a model-agnostic and easily scalable agent framework with three key components: constraint, verification, and selection agents. Specifically, our approach proposes constraint-guided iterative verification to enhance performance of inference-time algorithms--Best of N, Tree-of-Thought, and REBASE. In PlanGEN framework, the selection agent optimizes algorithm choice based on instance complexity, ensuring better adaptability to complex planning problems. Experimental results demonstrate significant improvements over the strongest baseline across multiple benchmarks, achieving state-of-the-art results on NATURAL PLAN ($\sim$8%$\uparrow$), OlympiadBench ($\sim$4%$\uparrow$), DocFinQA ($\sim$7%$\uparrow$), and GPQA ($\sim$1%$\uparrow$). Our key finding highlights that constraint-guided iterative verification improves inference-time algorithms, and adaptive selection further boosts performance on complex planning and reasoning problems.

Shangbin Feng, Zifeng Wang, Palash Goyal et al. · berkeley

We propose Heterogeneous Swarms, an algorithm to design multi-LLM systems by jointly optimizing model roles and weights. We represent multi-LLM systems as directed acyclic graphs (DAGs) of LLMs with topological message passing for collaborative generation. Given a pool of LLM experts and a utility function, Heterogeneous Swarms employs two iterative steps: role-step and weight-step. For role-step, we interpret model roles as learning a DAG that specifies the flow of inputs and outputs between LLMs. Starting from a swarm of random continuous adjacency matrices, we decode them into discrete DAGs, call the LLMs in topological order, evaluate on the utility function (e.g. accuracy on a task), and optimize the adjacency matrices with particle swarm optimization based on the utility score. For weight-step, we assess the contribution of individual LLMs in the multi-LLM systems and optimize model weights with swarm intelligence. We propose JFK-score to quantify the individual contribution of each LLM in the best-found DAG of the role-step, then optimize model weights with particle swarm optimization based on the JFK-score. Experiments demonstrate that Heterogeneous Swarms outperforms 15 role- and/or weight-based baselines by 18.5% on average across 12 tasks. Further analysis reveals that Heterogeneous Swarms discovers multi-LLM systems with heterogeneous model roles and substantial collaborative gains, and benefits from the diversity of language models.

Palash Goyal, Qian Hu, Rahul Gupta · amazon-science

Statistical significance testing is used in natural language processing (NLP) to determine whether the results of a study or experiment are likely to be due to chance or if they reflect a genuine relationship. A key step in significance testing is the estimation of confidence interval which is a function of sample variance. Sample variance calculation is straightforward when evaluating against ground truth. However, in many cases, a metric model is often used for evaluation. For example, to compare toxicity of two large language models, a toxicity classifier is used for evaluation. Existing works usually do not consider the variance change due to metric model errors, which can lead to wrong conclusions. In this work, we establish the mathematical foundation of significance testing for model-based metrics. With experiments on public benchmark datasets and a production system, we show that considering metric model errors to calculate sample variances for model-based metrics changes the conclusions in certain experiments.

Zhuohang Li, Xiaowei Li, Chengyu Huang et al.

The alignment of large language models (LLMs) with human values increasingly relies on using other LLMs as automated judges, or ``autoraters''. However, their reliability is limited by a foundational issue: they are trained on discrete preference labels, forcing a single ground truth onto tasks that are often subjective, ambiguous, or nuanced. We argue that a reliable autorater must learn to model the full distribution of preferences defined by a target population. In this paper, we propose a general framework for calibrating probabilistic autoraters to any given preference distribution. We formalize the problem and present two learning methods tailored to different data conditions: 1) a direct supervised fine-tuning for dense, probabilistic labels, and 2) a reinforcement learning approach for sparse, binary labels. Our empirical results show that finetuning autoraters with a distribution-matching objective leads to verbalized probability predictions that are better aligned with the target preference distribution, with improved calibration and significantly lower positional bias, all while preserving performance on objective tasks.

Gabriela Pinto, Palash Goyal, Yiwen Song et al.

Test-time scaling has shown considerable success in improving the performance of language models on complex reasoning tasks without requiring fine-tuning. However, current strategies such as self-reflection primarily focus on logical or structural refinement. They do not leverage the guiding potential of affective feedback. Inspired by psychological research showing that emotions can modulate cognitive performance, we introduce HEART--a novel framework that uses emotionally-driven prompts for iterative self-correction. HEART provides feedback on a model's incorrect response using a curated set of concise, emotionally charged phrases based on the six universal emotions categorized by Dr. Paul Ekman. By systematically varying the emotional tone of the feedback across iterations, our method guides the model to escape flawed reasoning paths and explore more promising alternatives. We evaluate our framework on challenging reasoning benchmarks including OlympiadBench, Humanity's Last Exam, and SimpleQA. Our results reveal a significant new phenomenon: when guided by an oracle verifier, this affective iteration protocol unlocks significantly deeper reasoning, leading to consistent and substantial increases in accuracy over state-of-the-art baselines with the same verifier. However, we also identify a critical bottleneck for practical deployment. In a verifier-free setting, it struggles to harness these gains consistently, highlighting as a key challenge for future work. Our findings suggest that the next frontier in machine reasoning may lie not just in refining logic, but also in understanding and leveraging the `HEART' of the models.

Anaelia Ovalle, Palash Goyal, Jwala Dhamala et al.

Transgender and non-binary (TGNB) individuals disproportionately experience discrimination and exclusion from daily life. Given the recent popularity and adoption of language generation technologies, the potential to further marginalize this population only grows. Although a multitude of NLP fairness literature focuses on illuminating and addressing gender biases, assessing gender harms for TGNB identities requires understanding how such identities uniquely interact with societal gender norms and how they differ from gender binary-centric perspectives. Such measurement frameworks inherently require centering TGNB voices to help guide the alignment between gender-inclusive NLP and whom they are intended to serve. Towards this goal, we ground our work in the TGNB community and existing interdisciplinary literature to assess how the social reality surrounding experienced marginalization of TGNB persons contributes to and persists within Open Language Generation (OLG). This social knowledge serves as a guide for evaluating popular large language models (LLMs) on two key aspects: (1) misgendering and (2) harmful responses to gender disclosure. To do this, we introduce TANGO, a dataset of template-based real-world text curated from a TGNB-oriented community. We discover a dominance of binary gender norms reflected by the models; LLMs least misgendered subjects in generated text when triggered by prompts whose subjects used binary pronouns. Meanwhile, misgendering was most prevalent when triggering generation with singular they and neopronouns. When prompted with gender disclosures, TGNB disclosure generated the most stigmatizing language and scored most toxic, on average. Our findings warrant further research on how TGNB harms manifest in LLMs and serve as a broader case study toward concretely grounding the design of gender-inclusive AI in community voices and interdisciplinary literature.

Saurabh Sahu, Palash Goyal

Robust video scene classification models should capture the spatial (pixel-wise) and temporal (frame-wise) characteristics of a video effectively. Transformer models with self-attention which are designed to get contextualized representations for individual tokens given a sequence of tokens, are becoming increasingly popular in many computer vision tasks. However, the use of Transformer based models for video understanding is still relatively unexplored. Moreover, these models fail to exploit the strong temporal relationships between the neighboring video frames to get potent frame-level representations. In this paper, we propose a novel self-attention block that leverages both local and global temporal relationships between the video frames to obtain better contextualized representations for the individual frames. This enables the model to understand the video at various granularities. We illustrate the performance of our models on the large scale YoutTube-8M data set on the task of video categorization and further analyze the results to showcase improvement.

Divya Choudhary, Palash Goyal, Saurabh Sahu

Deep neural networks have been shown to perform poorly on adversarial examples. To address this, several techniques have been proposed to increase robustness of a model for image classification tasks. However, in video understanding tasks, developing adversarially robust models is still unexplored. In this paper, we aim to bridge this gap. We first show that simple extensions of image based adversarially robust models slightly improve the worst-case performance. Further, we propose a temporal attention regularization scheme in Transformer to improve the robustness of attention modules to adversarial examples. We illustrate using a large-scale video data set YouTube-8M that the final model (A-ART) achieves close to non-adversarial performance on its adversarial example set. We achieve 91% GAP on adversarial examples, whereas baseline Transformer and simple adversarial extensions achieve 72.9% and 82% respectively, showing significant improvement in robustness over the state-of-the-art.

Saurabh Sahu, Palash Goyal

The introduction of Transformer model has led to tremendous advancements in sequence modeling, especially in text domain. However, the use of attention-based models for video understanding is still relatively unexplored. In this paper, we introduce Gated Adversarial Transformer (GAT) to enhance the applicability of attention-based models to videos. GAT uses a multi-level attention gate to model the relevance of a frame based on local and global contexts. This enables the model to understand the video at various granularities. Further, GAT uses adversarial training to improve model generalization. We propose temporal attention regularization scheme to improve the robustness of attention modules to adversarial examples. We illustrate the performance of GAT on the large-scale YoutTube-8M data set on the task of video categorization. We further show ablation studies along with quantitative and qualitative analysis to showcase the improvement.

Palash Goyal, Shalini Ghosh

Classification algorithms in machine learning often assume a flat label space. However, most real world data have dependencies between the labels, which can often be captured by using a hierarchy. Utilizing this relation can help develop a model capable of satisfying the dependencies and improving model accuracy and interpretability. Further, as different levels in the hierarchy correspond to different granularities, penalizing each label equally can be detrimental to model learning. In this paper, we propose a loss function, hierarchical curriculum loss, with two properties: (i) satisfy hierarchical constraints present in the label space, and (ii) provide non-uniform weights to labels based on their levels in the hierarchy, learned implicitly by the training paradigm. We theoretically show that the proposed loss function is a tighter bound of 0-1 loss compared to any other loss satisfying the hierarchical constraints. We test our loss function on real world image data sets, and show that it significantly substantially outperforms multiple baselines.

Palash Goyal, Saurabh Sahu, Shalini Ghosh et al.

Multi-modal machine learning (ML) models can process data in multiple modalities (e.g., video, audio, text) and are useful for video content analysis in a variety of problems (e.g., object detection, scene understanding, activity recognition). In this paper, we focus on the problem of video categorization using a multi-modal ML technique. In particular, we have developed a novel multi-modal ML approach that we call "cross-modal learning", where one modality influences another but only when there is correlation between the modalities -- for that, we first train a correlation tower that guides the main multi-modal video categorization tower in the model. We show how this cross-modal principle can be applied to different types of models (e.g., RNN, Transformer, NetVLAD), and demonstrate through experiments how our proposed multi-modal video categorization models with cross-modal learning out-perform strong state-of-the-art baseline models.

Palash Goyal, Saurabh Sahu, Shalini Ghosh et al.

Multimodal ML models can process data in multiple modalities (e.g., video, images, audio, text) and are useful for video content analysis in a variety of problems (e.g., object detection, scene understanding). In this paper, we focus on the problem of video categorization by using a multimodal approach. We have developed a novel temporal coherence-based regularization approach, which applies to different types of models (e.g., RNN, NetVLAD, Transformer). We demonstrate through experiments how our proposed multimodal video categorization models with temporal coherence out-perform strong state-of-the-art baseline models.

Arquimedes Canedo, Palash Goyal, Di Huang et al.

Automation engineering is the task of integrating, via software, various sensors, actuators, and controls for automating a real-world process. Today, automation engineering is supported by a suite of software tools including integrated development environments (IDE), hardware configurators, compilers, and runtimes. These tools focus on the automation code itself, but leave the automation engineer unassisted in their decision making. This can lead to increased time for software development because of imperfections in decision making leading to multiple iterations between software and hardware. To address this, this paper defines multiple challenges often faced in automation engineering and propose solutions using machine learning to assist engineers tackle such challenges. We show that machine learning can be leveraged to assist the automation engineer in classifying automation, finding similar code snippets, and reasoning about the hardware selection of sensors and actuators. We validate our architecture on two real datasets consisting of 2,927 Arduino projects, and 683 Programmable Logic Controller (PLC) projects. Our results show that paragraph embedding techniques can be utilized to classify automation using code snippets with precision close to human annotation, giving an F1-score of 72%. Further, we show that such embedding techniques can help us find similar code snippets with high accuracy. Finally, we use autoencoder models for hardware recommendation and achieve a p@3 of 0.79 and p@5 of 0.95.

Palash Goyal, Di Huang, Sujit Rokka Chhetri et al.

Representation learning on graphs has been gaining attention due to its wide applicability in predicting missing links, and classifying and recommending nodes. Most embedding methods aim to preserve certain properties of the original graph in the low dimensional space. However, real world graphs have a combination of several properties which are difficult to characterize and capture by a single approach. In this work, we introduce the problem of graph representation ensemble learning and provide a first of its kind framework to aggregate multiple graph embedding methods efficiently. We provide analysis of our framework and analyze -- theoretically and empirically -- the dependence between state-of-the-art embedding methods. We test our models on the node classification task on four real world graphs and show that proposed ensemble approaches can outperform the state-of-the-art methods by up to 8% on macro-F1. We further show that the approach is even more beneficial for underrepresented classes providing an improvement of up to 12%.

Palash Goyal, Sujit Rokka Chhetri, Arquimedes Canedo

Learning graph representations is a fundamental task aimed at capturing various properties of graphs in vector space. The most recent methods learn such representations for static networks. However, real world networks evolve over time and have varying dynamics. Capturing such evolution is key to predicting the properties of unseen networks. To understand how the network dynamics affect the prediction performance, we propose an embedding approach which learns the structure of evolution in dynamic graphs and can predict unseen links with higher precision. Our model, dyngraph2vec, learns the temporal transitions in the network using a deep architecture composed of dense and recurrent layers. We motivate the need of capturing dynamics for prediction on a toy data set created using stochastic block models. We then demonstrate the efficacy of dyngraph2vec over existing state-of-the-art methods on two real world data sets. We observe that learning dynamics can improve the quality of embedding and yield better performance in link prediction.

Jiang Wan, Blake S. Pollard, Sujit Rokka Chhetri et al.

The digitalization of automation engineering generates large quantities of engineering data that is interlinked in knowledge graphs. Classifying and clustering subgraphs according to their functionality is useful to discover functionally equivalent engineering artifacts that exhibit different graph structures. This paper presents a new graph learning algorithm designed to classify engineering data artifacts -- represented in the form of graphs -- according to their structure and neighborhood features. Our Structural Graph Convolutional Neural Network (SGCNN) is capable of learning graphs and subgraphs with a novel graph invariant convolution kernel and downsampling/pooling algorithm. On a realistic engineering-related dataset, we show that SGCNN is capable of achieving ~91% classification accuracy.

Palash Goyal, KSM Tozammel Hossain, Ashok Deb et al.

Cyber attacks are growing in frequency and severity. Over the past year alone we have witnessed massive data breaches that stole personal information of millions of people and wide-scale ransomware attacks that paralyzed critical infrastructure of several countries. Combating the rising cyber threat calls for a multi-pronged strategy, which includes predicting when these attacks will occur. The intuition driving our approach is this: during the planning and preparation stages, hackers leave digital traces of their activities on both the surface web and dark web in the form of discussions on platforms like hacker forums, social media, blogs and the like. These data provide predictive signals that allow anticipating cyber attacks. In this paper, we describe machine learning techniques based on deep neural networks and autoregressive time series models that leverage external signals from publicly available Web sources to forecast cyber attacks. Performance of our framework across ground truth data over real-world forecasting tasks shows that our methods yield a significant lift or increase of F1 for the top signals on predicted cyber attacks. Our results suggest that, when deployed, our system will be able to provide an effective line of defense against various types of targeted cyber attacks.

Sahil Garg, Irina Rish, Guillermo Cecchi et al.

We propose a novel dialogue modeling framework, the first-ever nonparametric kernel functions based approach for dialogue modeling, which learns kernelized hashcodes as compressed text representations; unlike traditional deep learning models, it handles well relatively small datasets, while also scaling to large ones. We also derive a novel lower bound on mutual information, used as a model-selection criterion favoring representations with better alignment between the utterances of participants in a collaborative dialogue setting, as well as higher predictability of the generated responses. As demonstrated on three real-life datasets, including prominently psychotherapy sessions, the proposed approach significantly outperforms several state-of-art neural network based dialogue systems, both in terms of computational efficiency, reducing training time from days or weeks to hours, and the response quality, achieving an order of magnitude improvement over competitors in frequency of being chosen as the best model by human evaluators.