arXiv subjects

Ritwik Sinha

Publications and source records attributed to Ritwik Sinha.

At least 19 recordsLinked to original sources

arXiv2026

Toward Latent Language Model Skills Steering and Optimization: An Empirical Study

Skills, as a useful abstraction for the procedural capabilities of large language models (LLMs), capture how models perform structured, multi-step reasoning and program execution. Existing approaches typically treat skills as explicit, surface-level constructs specified through prompts or programs, leaving open the question of how such procedural capabilities are represented inside the model and whether they can be manipulated as structured objects in latent space. In this empirical study, we investigate whether procedural LLM skills can be represented as directions in activation space and whether vector-space operations over these directions can express skill-level behaviors. We find that procedural skills admit a vector-space representation: individual skill directions can be activated to shift model behavior; independently extracted directions can compose to form higher-level skills. Contrastive directions yield context-conditioned algorithmic personalization and optimization trajectories over skill directions evolve non-monotonically, with intermediate states often surpassing fully optimized solutions. These results support a representation-level view of procedural LLM skills: they admit a latent vector-space organization that allows direct manipulation through internal interventions.

cs.AI↗

arXiv2026

BACON: Budgeted Human Calibration for Modeling and Evaluation with Multiple AI Judges

AI judges offer a scalable, low-cost alternative to human evaluation, but their outputs can be biased relative to human preferences and highly item-dependent, varying across judges, tasks, and domains. When uncalibrated AI evaluations are used for model ranking, item scoring, or population-level quality reporting, these biases can directly distort downstream decisions. We propose BACON, a four-stage pipeline that combines budgeted human calibration with multiple AI-judge outputs to produce more accurate annotations. BACON constructs full-coverage auxiliary features for every item, including multi-judge scores, token-level uncertainty statistics, and contextual embeddings. It then collects human labels for a small sampled subset and trains a cross-fitted outcome model to generate calibrated item-level surrogate predictions. These predictions support two use cases: population-level estimation of summary metrics, such as means or quantiles, using an augmented estimating-equation estimator with valid confidence intervals; and individual-level surrogate scoring for item ranking and annotation. BACON treats AI judges as auxiliary measurements rather than ground truth: human labels provide the calibration anchor, while AI-derived signals improve efficiency. Across diverse tasks, domains, and labeling budgets, BACON improves predictive accuracy and ranking consistency, and reduces bias and variance relative to raw AI outputs and purely human-label-based methods. These results show that BACON offers a practical, statistically grounded framework for scalable evaluation with limited human annotation.

cs.LG↗

arXiv2026

F-GRPO: Factorized Group-Relative Policy Optimization for Unified Candidate Generation and Ranking

Traditional retrieval pipelines optimize utility through stages of candidate retrieval and reranking, where ranking operates over a predefined candidate set. Large Language Models (LLMs) broaden this into a generative process: given a candidate pool, an LLM can generate a subset and order it within a single autoregressive pass. However, this flexibility introduces a new optimization challenge: the model must search a combinatorial output space while receiving utility feedback only after the full ranked list is generated. Because this feedback is defined over the completed sequence, it cannot distinguish whether a poor result arises from failing to generate a relevant subset or from failing to rank that subset correctly. This credit assignment gap makes end-to-end optimization unstable and sample-inefficient. Existing systems often address this by separating candidate generation from ranking. However, such decoupling remains misaligned with downstream utility because ranking is limited by the candidate set it receives. To bridge this gap, we propose a unified framework that performs both within a single autoregressive rollout and optimizes them end-to-end via factorized group-relative policy optimization (F-GRPO). Our framework factorizes the policy into candidate generation and ranking while sharing a single LLM backbone, and jointly trains them with an order-invariant coverage reward and a position-aware utility reward. To address the resulting phase-specific credit assignment problem, we use separate group-relative advantages for generation and ranking within a two-phase sequence-level objective. Across sequential recommendation and multi-hop question answering benchmarks, F-GRPO improves top-ranked performance over GRPO and decoupled baselines, outperforms supervised alternatives, and remains competitive with strong zero-shot rerankers, with no architectural changes at inference time.

cs.LG↗

arXiv2026

Experimentation Accelerator: Interpretable Insights and Creative Recommendations for A/B Testing with Content-Aware ranking

Modern online experimentation faces two bottlenecks: scarce traffic forces tough choices on which variants to test, and post-hoc insight extraction is manual, inconsistent, and often content-agnostic. Meanwhile, organizations underuse historical A/B results and rich content embeddings that could guide prioritization and creative iteration. We present a unified framework to (i) prioritize which variants to test, (ii) explain why winners win, and (iii) surface targeted opportunities for new, higher-potential variants. Leveraging treatment embeddings and historical outcomes, we train a CTR ranking model with fixed effects for contextual shifts that scores candidates while balancing value and content diversity. For better interpretability and understanding, we project treatments onto curated semantic marketing attributes and re-express the ranker in this space via a sign-consistent, sparse constrained Lasso, yielding per-attribute coefficients and signed contributions for visual explanations, top-k drivers, and natural-language insights. We then compute an opportunity index combining attribute importance (from the ranker) with under-expression in the current experiment to flag missing, high-impact attributes. Finally, LLMs translate ranked opportunities into concrete creative suggestions and estimate both learning and conversion potential, enabling faster, more informative, and more efficient test cycles. These components have been built into a real Adobe product, called \textit{Experimentation Accelerator}, to provide AI-based insights and opportunities to scale experimentation for customers. We provide an evaluation of the performance of the proposed framework on some real-world experiments by Adobe business customers that validate the high quality of the generation pipeline.

cs.AI↗

arXiv2025

Leveraging semantic similarity for experimentation with AI-generated treatments

Large Language Models (LLMs) enable a new form of digital experimentation where treatments combine human and model-generated content in increasingly sophisticated ways. The main methodological challenge in this setting is representing these high-dimensional treatments without losing their semantic meaning or rendering analysis intractable. Here, we address this problem by focusing on learning low-dimensional representations that capture the underlying structure of such treatments. These representations enable downstream applications such as guiding generative models to produce meaningful treatment variants and facilitating adaptive assignment in online experiments. We propose double kernel representation learning, which models the causal effect through the inner product of kernel-based representations of treatments and user covariates. We develop an alternating-minimization algorithm that learns these representations efficiently from data and provides convergence guarantees under a low-rank factor model. As an application of this framework, we introduce an adaptive design strategy for online experimentation and demonstrate the method's effectiveness through numerical experiments.

stat.ME↗

arXiv2025

Explainable Chain-of-Thought Reasoning: An Empirical Analysis on State-Aware Reasoning Dynamics

Recent advances in chain-of-thought (CoT) prompting have enabled large language models (LLMs) to perform multi-step reasoning. However, the explainability of such reasoning remains limited, with prior work primarily focusing on local token-level attribution, such that the high-level semantic roles of reasoning steps and their transitions remain underexplored. In this paper, we introduce a state-aware transition framework that abstracts CoT trajectories into structured latent dynamics. Specifically, to capture the evolving semantics of CoT reasoning, each reasoning step is represented via spectral analysis of token-level embeddings and clustered into semantically coherent latent states. To characterize the global structure of reasoning, we model their progression as a Markov chain, yielding a structured and interpretable view of the reasoning process. This abstraction supports a range of analyses, including semantic role identification, temporal pattern visualization, and consistency evaluation.

cs.CL↗

arXiv2025

Exploring Rewriting Approaches for Different Conversational Tasks

Conversational assistants often require a question rewriting algorithm that leverages a subset of past interactions to provide a more meaningful (accurate) answer to the user's question or request. However, the exact rewriting approach may often depend on the use case and application-specific tasks supported by the conversational assistant, among other constraints. In this paper, we systematically investigate two different approaches, denoted as rewriting and fusion, on two fundamentally different generation tasks, including a text-to-text generation task and a multimodal generative task that takes as input text and generates a visualization or data table that answers the user's question. Our results indicate that the specific rewriting or fusion approach highly depends on the underlying use case and generative task. In particular, we find that for a conversational question-answering assistant, the query rewriting approach performs best, whereas for a data analysis assistant that generates visualizations and data tables based on the user's conversation with the assistant, the fusion approach works best. Notably, we explore two datasets for the data analysis assistant use case, for short and long conversations, and we find that query fusion always performs better, whereas for the conversational text-based question-answering, the query rewrite approach performs best.

cs.CL↗

arXiv2024

BOTracle: A framework for Discriminating Bots and Humans

Bots constitute a significant portion of Internet traffic and are a source of various issues across multiple domains. Modern bots often become indistinguishable from real users, as they employ similar methods to browse the web, including using real browsers. We address the challenge of bot detection in high-traffic scenarios by analyzing three distinct detection methods. The first method operates on heuristics, allowing for rapid detection. The second method utilizes, well known, technical features, such as IP address, window size, and user agent. It serves primarily for comparison with the third method. In the third method, we rely solely on browsing behavior, omitting all static features and focusing exclusively on how clients behave on a website. In contrast to related work, we evaluate our approaches using real-world e-commerce traffic data, comprising 40 million monthly page visits. We further compare our methods against another bot detection approach, Botcha, on the same dataset. Our performance metrics, including precision, recall, and AUC, reach 98 percent or higher, surpassing Botcha.

cs.LG↗

arXiv2024

Diversify-verify-adapt: Efficient and Robust Retrieval-Augmented Ambiguous Question Answering

The retrieval augmented generation (RAG) framework addresses an ambiguity in user queries in QA systems by retrieving passages that cover all plausible interpretations and generating comprehensive responses based on the passages. However, our preliminary studies reveal that a single retrieval process often suffers from low quality results, as the retrieved passages frequently fail to capture all plausible interpretations. Although the iterative RAG approach has been proposed to address this problem, it comes at the cost of significantly reduced efficiency. To address these issues, we propose the diversify-verify-adapt (DIVA) framework. DIVA first diversifies the retrieved passages to encompass diverse interpretations. Subsequently, DIVA verifies the quality of the passages and adapts the most suitable approach tailored to their quality. This approach improves the QA systems accuracy and robustness by handling low quality retrieval issue in ambiguous questions, while enhancing efficiency.

cs.CL↗

arXiv2024

A/B testing under Interference with Partial Network Information

A/B tests are often required to be conducted on subjects that might have social connections. For e.g., experiments on social media, or medical and social interventions to control the spread of an epidemic. In such settings, the SUTVA assumption for randomized-controlled trials is violated due to network interference, or spill-over effects, as treatments to group A can potentially also affect the control group B. When the underlying social network is known exactly, prior works have demonstrated how to conduct A/B tests adequately to estimate the global average treatment effect (GATE). However, in practice, it is often impossible to obtain knowledge about the exact underlying network. In this paper, we present UNITE: a novel estimator that relax this assumption and can identify GATE while only relying on knowledge of the superset of neighbors for any subject in the graph. Through theoretical analysis and extensive experiments, we show that the proposed approach performs better in comparison to standard estimators.

cs.LG↗

arXiv2024

Continuous Treatment Effects with Surrogate Outcomes

In many real-world causal inference applications, the primary outcomes (labels) are often partially missing, especially if they are expensive or difficult to collect. If the missingness depends on covariates (i.e., missingness is not completely at random), analyses based on fully observed samples alone may be biased. Incorporating surrogates, which are fully observed post-treatment variables related to the primary outcome, can improve estimation in this case. In this paper, we study the role of surrogates in estimating continuous treatment effects and propose a doubly robust method to efficiently incorporate surrogates in the analysis, which uses both labeled and unlabeled data and does not suffer from the above selection bias problem. Importantly, we establish the asymptotic normality of the proposed estimator and show possible improvements on the variance compared with methods that solely use labeled data. Extensive simulations show our methods enjoy appealing empirical performance.

stat.ML↗

arXiv2024

Augment before You Try: Knowledge-Enhanced Table Question Answering via Table Expansion

Table question answering is a popular task that assesses a model's ability to understand and interact with structured data. However, the given table often does not contain sufficient information for answering the question, necessitating the integration of external knowledge. Existing methods either convert both the table and external knowledge into text, which neglects the structured nature of the table; or they embed queries for external sources in the interaction with the table, which complicates the process. In this paper, we propose a simple yet effective method to integrate external information in a given table. Our method first constructs an augmenting table containing the missing information and then generates a SQL query over the two tables to answer the question. Experiments show that our method outperforms strong baselines on three table QA benchmarks. Our code is publicly available at https://github.com/UCSB-NLP-Chang/Augment_tableQA.

cs.CL↗

arXiv2023

SODA: Protecting Proprietary Information in On-Device Machine Learning Models

The growth of low-end hardware has led to a proliferation of machine learning-based services in edge applications. These applications gather contextual information about users and provide some services, such as personalized offers, through a machine learning (ML) model. A growing practice has been to deploy such ML models on the user's device to reduce latency, maintain user privacy, and minimize continuous reliance on a centralized source. However, deploying ML models on the user's edge device can leak proprietary information about the service provider. In this work, we investigate on-device ML models that are used to provide mobile services and demonstrate how simple attacks can leak proprietary information of the service provider. We show that different adversaries can easily exploit such models to maximize their profit and accomplish content theft. Motivated by the need to thwart such attacks, we present an end-to-end framework, SODA, for deploying and serving on edge devices while defending against adversarial usage. Our results demonstrate that SODA can detect adversarial usage with 89% accuracy in less than 50 queries with minimal impact on service performance, latency, and storage.

cs.LG↗

arXiv2023

A Mathematical Abstraction for Balancing the Trade-off Between Creativity and Reality in Large Language Models

Large Language Models have become popular for their remarkable capabilities in human-oriented tasks and traditional natural language processing tasks. Its efficient functioning is attributed to the attention mechanism in the Transformer architecture, enabling it to concentrate on particular aspects of the input. LLMs are increasingly being used in domains such as generating prose, poetry or art, which require the model to be creative (e.g. Adobe firefly). LLMs possess advanced language generation abilities that enable them to generate distinctive and captivating content. This utilization of LLMs in generating narratives shows their flexibility and potential for use in domains that extend beyond conventional natural language processing duties. In different contexts, we may expect the LLM to generate factually correct answers, that match reality; e.g., question-answering systems or online assistants. In such situations, being correct is critical to LLMs being trusted in practice. The Bing Chatbot provides its users with the flexibility to select one of the three output modes: creative, balanced, and precise. Each mode emphasizes creativity and factual accuracy differently. In this work, we provide a mathematical abstraction to describe creativity and reality based on certain losses. A model trained on these losses balances the trade-off between the creativity and reality of the model.

cs.CL↗

arXiv2023

VADER: Video Alignment Differencing and Retrieval

We propose VADER, a spatio-temporal matching, alignment, and change summarization method to help fight misinformation spread via manipulated videos. VADER matches and coarsely aligns partial video fragments to candidate videos using a robust visual descriptor and scalable search over adaptively chunked video content. A transformer-based alignment module then refines the temporal localization of the query fragment within the matched video. A space-time comparator module identifies regions of manipulation between aligned content, invariant to any changes due to any residual temporal misalignments or artifacts arising from non-editorial changes of the content. Robustly matching video to a trusted source enables conclusions to be drawn on video provenance, enabling informed trust decisions on content encountered.

cs.CV↗

arXiv2023

Anytime-Valid Confidence Sequences in an Enterprise A/B Testing Platform

A/B tests are the gold standard for evaluating digital experiences on the web. However, traditional "fixed-horizon" statistical methods are often incompatible with the needs of modern industry practitioners as they do not permit continuous monitoring of experiments. Frequent evaluation of fixed-horizon tests ("peeking") leads to inflated type-I error and can result in erroneous conclusions. We have released an experimentation service on the Adobe Experience Platform based on anytime-valid confidence sequences, allowing for continuous monitoring of the A/B test and data-dependent stopping. We demonstrate how we adapted and deployed asymptotic confidence sequences in a full featured A/B testing platform, describe how sample size calculations can be performed, and how alternate test statistics like "lift" can be analyzed. On both simulated data and thousands of real experiments, we show the desirable properties of using anytime-valid methods instead of traditional approaches.

stat.AP↗

arXiv2022

Privacy Aware Experiments without Cookies

Consider two brands that want to jointly test alternate web experiences for their customers with an A/B test. Such collaborative tests are today enabled using \textit{third-party cookies}, where each brand has information on the identity of visitors to another website. With the imminent elimination of third-party cookies, such A/B tests will become untenable. We propose a two-stage experimental design, where the two brands only need to agree on high-level aggregate parameters of the experiment to test the alternate experiences. Our design respects the privacy of customers. We propose an estimater of the Average Treatment Effect (ATE), show that it is unbiased and theoretically compute its variance. Our demonstration describes how a marketer for a brand can design such an experiment and analyze the results. On real and simulated data, we show that the approach provides valid estimate of the ATE with low variance and is robust to the proportion of visitors overlapping across the brands.

stat.ME↗

arXiv2022

Video Manipulations Beyond Faces: A Dataset with Human-Machine Analysis

As tools for content editing mature, and artificial intelligence (AI) based algorithms for synthesizing media grow, the presence of manipulated content across online media is increasing. This phenomenon causes the spread of misinformation, creating a greater need to distinguish between ``real'' and ``manipulated'' content. To this end, we present VideoSham, a dataset consisting of 826 videos (413 real and 413 manipulated). Many of the existing deepfake datasets focus exclusively on two types of facial manipulations -- swapping with a different subject's face or altering the existing face. VideoSham, on the other hand, contains more diverse, context-rich, and human-centric, high-resolution videos manipulated using a combination of 6 different spatial and temporal attacks. Our analysis shows that state-of-the-art manipulation detection algorithms only work for a few specific attacks and do not scale well on VideoSham. We performed a user study on Amazon Mechanical Turk with 1200 participants to understand if they can differentiate between the real and manipulated videos in VideoSham. Finally, we dig deeper into the strengths and weaknesses of performances by humans and SOTA-algorithms to identify gaps that need to be filled with better AI algorithms. We present the dataset at https://github.com/adobe-research/VideoSham-dataset.

cs.CV↗