Papers by Rahul Gupta

TableFormer: Robust Transformer Modeling for Table-Text Encoding (2022.acl-long)

Challenge:	Recent studies have explored using LLMs for efficient data collection.
Approach:	They propose a method that takes into account the characteristics of the desired dataset and monitors the status of the generated data.
Outcome:	The proposed method improves safety and quality of three representative large language models against safety issues without sacrificing model utility.

Copied to clipboard

Jingfeng Yang, Aditya Gupta, Shyam Upadhyay, Luheng He, Rahul Goel, Shachi Paul

Improving Top-K Decoding for Non-Autoregressive Semantic Parsing via Intent Conditioning (2022.coling-1)

Challenge:	Existing tables models require linearization of the table structure, where row or column order is encoded as an unwanted bias.
Approach:	They propose a robust and structurally aware table-text encoding architecture TableFormer where tabular structural biases are incorporated completely through learnable attention biase.
Outcome:	The proposed architecture outperforms strong baselines on SQA, WTQ and TabFact table reasoning datasets and achieves state-of-the-art performance on SQ.

Copied to clipboard

Geunseob Oh, Rahul Goel, Chris Hidey, Shachi Paul, Aditya Gupta, Pararth Shah, Rushin Shah

Diagnosing Memorization in Chain-of-Thought Reasoning, One Token at a Time (2025.emnlp-main)

Challenge:	Semantic parsing (SP) is a core component of modern virtual assistants like Google Assistant and Amazon Alexa.
Approach:	They propose a non-autoregressive (NAR) semantic parser that introduces intent conditioning on the decoder.
Outcome:	The proposed model reduces inference latency while maintaining competitive parsing quality.

Copied to clipboard

Huihan Li, You Chen, Siyuan Wang, Yixin He, Ninareh Mehrabi, Rahul Gupta, Xiang Ren

Reasoning

Challenge:	Large Language Models (LLMs) perform well on reasoning benchmarks but often fail when inputs alter slightly, raising concerns about overreliance on memorization.
Approach:	They propose a framework for Source-aware Token-level Identification of Memorization which attributes each token in a reasoning chain to one of multiple memorization sources based on their statistical co-occurrence with the token in the pretraining corpus.
Outcome:	The proposed framework attributes each token in a reasoning chain to one of multiple memorization sources based on their statistical co-occurrence with the token in the pretraining corpus.

MICo: Preventative Detoxification of Large Language Models through Inhibition Control (2024.findings-naacl)

Copied to clipboard

Roy Siegelmann, Ninareh Mehrabi, Palash Goyal, Prasoon Goyal, Lisa Bauer, Jwala Dhamala, Aram Galstyan, Rahul Gupta, Reza Ghanadan

CARMO: Dynamic Criteria Generation for Context Aware Reward Modelling (2025.findings-acl)

Challenge:	Large Language Models (LLMs) have a tendency to devolve into toxic degeneration . model may classify prompts as toxic or non-toxic and categorically refuse to respond to those deemed toxic.
Approach:	They propose a mechanism for LLM detoxification by labeling acceptable and unacceptable examples and including a corresponding acceptable rewrite with every unacceptable example.
Outcome:	The proposed model improves on the baseline model and shows that it detects and rewrites toxic and harmful examples.

Copied to clipboard

Taneesh Gupta, Shivam Shandilya, Xuchao Zhang, Rahul Madhavan, Supriyo Ghosh, Chetan Bansal, Huaxiu Yao, Saravan Rajmohan

Challenge:	Reward modeling in large language models is susceptible to reward hacking . flawed reward signals often lead to outputs that optimize for spurious correlates .
Approach:	They propose a new approach that generates dynamic, context-relevant criteria to ground the reward model prior to producing reward scores.
Outcome:	The proposed approach generates dynamic, context-relevant criteria to ground the model prior to producing reward scores.

From Narrow Unlearning to Emergent Misalignment in LLMs (2026.acl-short)

Copied to clipboard

Erum Mushtaq, Anil Ramakrishna, Satyapriya Krishna, Sattvik Sahai, Prasoon Goyal, Kai-Wei Chang, Tao Zhang, Rahul Gupta

Challenge:	Recent work shows that fine-tuning on insecure code data can trigger an emergent misalignment (EMA) phenomenon .
Approach:	They extend their study by demonstrating that EMA can arise from narrow refusal unlearning . they perform refusal unLearning on Cybersecurity and Safety concept and evaluate EMA .
Outcome:	The proposed model can generate malicious responses even to unrelated prompts . the proposed model is able to restore alignment across the affected domains while having lower refusal rates.

MUTANT: A Multi-sentential Code-mixed Hinglish Dataset (2023.findings-eacl)

Copied to clipboard

Rahul Gupta, Vivek Srivastava, Mayank Singh

Multilinguality

Challenge:	Existing methods to identify code-mixed text are difficult to scale effectively and efficiently on multi-sentential data.
Approach:	They propose to identify multi-sentential code-mixed text (MCT) from multilingual articles using a token-level language-aware pipeline.
Outcome:	The proposed dataset includes 67k articles with 85k identified Hinglish MCTs.

On Localizing and Deleting Toxic Memories in Large Language Models (2025.findings-naacl)

Copied to clipboard

Anubrata Das, Manoj Kumar, Ninareh Mehrabi, Anil Ramakrishna, Anna Rumshisky, Kai-Wei Chang, Aram Galstyan, Morteza Ziyadi, Rahul Gupta

Multi-VALUE: A Framework for Cross-Dialectal English NLP (2023.acl-long)

Challenge:	Existing methods to reduce toxic generation in large language models are not fully understood.
Approach:	They propose to understand the mechanisms that drive toxic generation in large language models by using memory localization to reduce toxic generation.
Outcome:	The proposed method reduces toxic generation from 62.86% to 28.61%, but it also improves generation quality.

Copied to clipboard

Caleb Ziems, William Held, Jingfeng Yang, Jwala Dhamala, Rahul Gupta, Diyi Yang

Machine Translation

Challenge:	Current systems that focus on standard American English are not dialect invariant . current systems focus on a single dialect, which results in performance discrepancies .
Approach:	They propose a resource for evaluating and achieving English dialect invariance . they stress test question answering, machine translation, and semantic parsing .
Outcome:	The proposed system is based on a rule-based translation system spanning 50 English dialects and 189 unique linguistic features.

Self-contradictory reasoning evaluation and detection (2024.findings-emnlp)

Copied to clipboard

Ziyi Liu, Soumya Sanyal, Isabelle Lee, Yongkang Du, Rahul Gupta, Yang Liu, Jieyu Zhao

Coordinated Replay Sample Selection for Continual Federated Learning (2023.emnlp-industry)

Challenge:	Large language models (LLMs) have shown impressive reasoning ability, but many downstream reasoning tasks focus on performance-wise evaluation.
Approach:	They define and assess the Self-Contra rate across three datasets and delve into finer-grained categories of Self-contra reasoning.
Outcome:	The proposed model can detect self-contra reasoning with a 52.2% F1 score, much lower than for humans.

Copied to clipboard

Jack Good, Jimit Majmudar, Christophe Dupuy, Jixuan Wang, Charith Peris, Clement Chung, Richard Zemel, Rahul Gupta

Faithful Model Evaluation for Model-Based Metrics (2023.emnlp-main)

Challenge:	Continual Federated Learning (CFL) combines decentralized learning with continuous learning . ubiquity of personal devices with a network connection offers rich source of data for learning problems .
Approach:	They propose to combine decentralized learning with a continuous learning approach . they propose to coordinate gradient-based replay sample selection across clients .
Outcome:	The proposed method shows gains early in the low replay size regime, when the budget for storing past data is small.

Copied to clipboard

Qian Hu, Palash Goyal, Rahul Gupta

Challenge:	Existing studies do not consider variance change due to metric model errors, which can lead to wrong conclusions.
Approach:	They establish the mathematical foundation of significance testing for model-based metrics . they show that metric errors can change the conclusions in certain experiments .
Outcome:	The proposed method can be used to derive accurate conclusions using model evaluations.

On the Intrinsic and Extrinsic Fairness Evaluation Metrics for Contextualized Language Representations (2022.acl-short)

Copied to clipboard

Yang Trista Cao, Yada Pruksachatkun, Kai-Wei Chang, Rahul Gupta, Varun Kumar, Jwala Dhamala, Aram Galstyan

Evaluating Large Language Models on Controlled Generation Tasks (2023.emnlp-main)

Challenge:	Recent natural language processing systems use large language models as the backbone . however, societal biases are encoded in these models and transferred to downstream applications .
Approach:	They propose to use two categories to measure fairness in natural language processing tasks . they find intrinsic and extrinsic metrics do not correlate in their original setting .
Outcome:	The proposed metrics do not correlate in their original setting, the authors show . they find that they are not accurate when correcting for metric misalignments and noise .

Copied to clipboard

Jiao Sun, Yufei Tian, Wangchunshu Zhou, Nan Xu, Qian Hu, Rahul Gupta, John Wieting, Nanyun Peng, Xuezhe Ma

PRESTO: A Multilingual Dataset for Parsing Realistic Task-Oriented Dialogs (2023.emnlp-main)

Challenge:	Recent studies have looked into the ability of large language models in various benchmark tasks, including question generation, reading comprehension, multilingual and etc. However, few studies investigate the controllability of large languages.
Approach:	They propose to compare large language models with state-of-the-start finetuned smaller models to find that large language model controls are comparable to smaller models.
Outcome:	The proposed model can meet hard constraints and perform better than state-of-the-art models.

Copied to clipboard

Rahul Goel, Waleed Ammar, Aditya Gupta, Siddharth Vashishtha, Motoki Sano, Faiz Surani, Max Chang, HyunJeong Choe, David Greene, Chuan He, Rattima Nitisaroj, Anna Trukhina, Shachi Paul, Pararth Shah, Rushin Shah, Zhou Yu

Natural Language Interfaces

Challenge:	PRESTO dataset contains 550K contextual multilingual conversations between humans and virtual assistants.
Approach:	They propose to use a dataset of 550K contextual multilingual conversations between humans and virtual assistants to study some of the more challenging aspects of parsing realistic conversations.
Outcome:	The dataset contains 550K contextual conversations between humans and virtual assistants.

The steerability of large language models toward data-driven personas (2024.naacl-long)

Copied to clipboard

Junyi Li, Charith Peris, Ninareh Mehrabi, Palash Goyal, Kai-Wei Chang, Aram Galstyan, Richard Zemel, Rahul Gupta

INVITE: a Testbed of Automatically Generated Invalid Questions to Evaluate Large Language Models for Hallucinations (2023.findings-emnlp)

Challenge:	Large language models generate biased responses where opinions of certain groups and populations are underrepresented.
Approach:	They propose a data-driven notion of persona that allows for a more nuanced understanding of different (latent) social groups present in the population.
Outcome:	The proposed method improves model steerability by 57% over baselines.

Copied to clipboard

Anil Ramakrishna, Rahul Gupta, Jens Lehmann, Morteza Ziyadi

Attribute Controlled Fine-tuning for Large Language Models: A Case Study on Detoxification (2024.findings-emnlp)

Challenge:	Recent advances in Large language models have enabled them to hold free form conversations over multiple turns, but they exhibit a tendency to make unfounded and incorrect statements, commonly labeled as hallucinations.
Approach:	They propose a framework to test large language models for hallucinations using automatically generated INValId questions.
Outcome:	The proposed framework is based on a testbed of automatically generated INValId questions to evaluate large language models for hallucinations.

Copied to clipboard

Tao Meng, Ninareh Mehrabi, Palash Goyal, Anil Ramakrishna, Aram Galstyan, Richard Zemel, Kai-Wei Chang, Rahul Gupta, Charith Peris

Conditional Language Policy: A General Framework For Steerable Multi-Objective Finetuning (2024.findings-emnlp)

Challenge:	Using a sequence-level constraint, we regularize the LLMtraining by penalizing the KL divergence between the desired output distribution and the LRM’s posterior.
Approach:	They propose a constraint learning schema forfine-tuning Large Language Models with attribute control by penalizing the KL divergence be-tween the desired output distribution and the LLM's posterior.
Outcome:	The proposed approach improves the performance of large language models while enhancing their utility and generation quality.

Copied to clipboard

Kaiwen Wang, Rahul Kidambi, Ryan Sullivan, Alekh Agarwal, Christoph Dann, Andrea Michi, Marco Gelmi, Yunxuan Li, Raghav Gupta, Kumar Dubey, Alexandre Rame, Johan Ferret, Geoffrey Cideron, Le Hou, Hongkun Yu, Amr Ahmed, Aranyak Mehta, Leonard Hussenot, Olivier Bachem, Edouard Leurent

Not Every Token Needs Forgetting: Selective Unlearning Balancing Forgetting and Utility in Large Language Models (2025.findings-emnlp)

Challenge:	Existing approaches for multi-objective Reinforcement Learning (RL) are difficult due to plurality of preferences and applications.
Approach:	They propose a framework for finetuning language models on multiple objectives using conditional language policy.
Outcome:	The proposed framework outperforms and Pareto-dominates existing approaches for multi-objective Reinforcement Learning (RL) it does not require training or maintaining multiple models to achieve different trade-offs between the objectives.

Copied to clipboard

Yixin Wan, Anil Ramakrishna, Kai-Wei Chang, Volkan Cevher, Rahul Gupta

FLIRT: Feedback Loop In-context Red Teaming (2024.emnlp-main)

Challenge:	Conventional unlearning approaches forget all tokens in a target document, including common tokens that carry general knowledge.
Approach:	They propose a method that identifies a critical subset of tokens within the forgetting set that is relevant to the unwanted information and unlearns only those tokens.
Outcome:	Experiments on two benchmarks and six baseline unlearning algorithms show that selective unlearning achieves effective unlearning on the targeted forget data.

Copied to clipboard

Ninareh Mehrabi, Palash Goyal, Christophe Dupuy, Qian Hu, Shalini Ghosh, Richard Zemel, Kai-Wei Chang, Aram Galstyan, Rahul Gupta

Scaling Down, Serving Fast: Compressing and Deploying Efficient LLMs for Recommendation Systems (2025.emnlp-industry)

Challenge:	Recent work has evaluated the vulnerabilities of large generative models, such as DALL-E, ChatGPT, and GPT-4.
Approach:	They propose an automatic red teaming framework that evaluates a given black-box model and exposes its vulnerabilities against unsafe and inappropriate content generation.
Outcome:	The proposed framework evaluates a given black-box model and exposes its vulnerabilities against unsafe and inappropriate content generation.

Copied to clipboard

Kayhan Behdin, Ata Fatahibaarzi, Qingquan Song, Yun Dai, Aman Gupta, Zhipeng Wang, Hejian Sang, Shao Tang, Gregory Dexter, Sirou Zhu, Siyu Zhu, Tejas Dharamsi, Vignesh Kothapalli, Zhoutong Fu, Yihan Cao, Pin-Lun Hsu, Fedor Borisyuk, Natesh S. Pillai, Luke Simon, Rahul Mazumder

Tokenization Matters: Navigating Data-Scarce Tokenization for Gender Inclusive Language Technologies (2024.findings-naacl)

Challenge:	Large language models (LLMs) have demonstrated remarkable performance across a wide range of industrial applications.
Approach:	They propose two techniques for training and deploying small language models that deliver high performance for a variety of industry use cases.
Outcome:	The proposed techniques retain much of the quality of larger models while reducing training/serving costs and latency.

Copied to clipboard

Anaelia Ovalle, Ninareh Mehrabi, Palash Goyal, Jwala Dhamala, Kai-Wei Chang, Richard Zemel, Aram Galstyan, Yuval Pinter, Rahul Gupta

FedNLP: Benchmarking Federated Learning Methods for Natural Language Processing Tasks (2022.findings-naacl)

Challenge:	a recent study documented the harmful limitations of gender binary-centric large language models . data scarcity is a known culprit, but the precise mechanisms through which scarcity affects this behavior remain underexplored.
Approach:	They propose to use BPE tokenization to enforce consistent tokenization across gendered pronouns to improve neopronoun proficiency.
Outcome:	The proposed methods outperform finetuning with standard BPE, and improve neopronoun proficiency.

Copied to clipboard

Bill Yuchen Lin, Chaoyang He, Zihang Ze, Hulin Wang, Yufen Hua, Christophe Dupuy, Rahul Gupta, Mahdi Soltanolkotabi, Xiang Ren, Salman Avestimehr

Does Robustness Improve Fairness? Approaching Fairness with Word Substitution Robustness Methods for Text Classification (2021.findings-acl)

Challenge:	Increasing concerns and regulations about data privacy necessitate the study of privacy-preserving, decentralized learning methods for natural language processing tasks.
Approach:	They propose a framework for evaluating federated learning methods on four different tasks . they propose federation between Transformer-based language models and FL methods .
Outcome:	The proposed framework compares FL methods on four different tasks under non-IID partitioning strategies.

Copied to clipboard

Yada Pruksachatkun, Satyapriya Krishna, Jwala Dhamala, Rahul Gupta, Kai-Wei Chang

Mitigating Gender Bias in Distilled Language Models via Counterfactual Role Reversal (2022.findings-acl)

Challenge:	Existing methods to reduce disparities in model outcomes have focused on data augmentation, debiasing model embeddings, or adding fairness-based optimization objectives during training.
Approach:	They propose to use certified word substitution robustness methods to improve equality of odds and equality of opportunity on multiple text classification tasks.
Outcome:	The proposed methods improve equality of odds and equality of opportunity on multiple text classification tasks.

Copied to clipboard

Umang Gupta, Jwala Dhamala, Varun Kumar, Apurv Verma, Yada Pruksachatkun, Satyapriya Krishna, Rahul Gupta, Kai-Wei Chang, Greg Ver Steeg, Aram Galstyan

AutoSUIT Bench - Automated Security UnIt Test Benchmark for LLM Coding (2026.findings-acl)

Challenge:	Language models excel at generating coherent text, but can be biased in multiple ways, including the unfounded association of male and female genders with gender-neutral professions.
Approach:	They propose to modify teacher probabilities and augment the training set to learn a fair model during knowledge distillation by modifying teacher probability and augmenting the training sets.
Outcome:	The proposed approach reduces gender disparity in open-ended text generated from the distilled and finetuned models with only a minor compromise in utility.

Copied to clipboard

Samuel Osebe, Fan Yang, Junyi Li, Yue Gu, Yongxin Wang, Satyapriya Krishna, Kai-Wei Chang, Aram Galstyan, Rahul Gupta, Weitong Ruan

Programming Languages in NLP

Challenge:	Large Language Models (LLMs) are evolving rapidly on code generation tasks.
Approach:	They propose to automate the vulnerability code benchmark creation with iterative auto validation.
Outcome:	The proposed benchmark covers 232 CWE categories across C/C++, Java, and Python languages.

Measuring Fairness of Text Classifiers via Prediction Sensitivity (2022.acl-long)

Copied to clipboard

Satyapriya Krishna, Rahul Gupta, Apurv Verma, Jwala Dhamala, Yada Pruksachatkun, Kai-Wei Chang

Text Classification

Challenge:	Existing fairness metrics are not yet available to measure the fairness of language processing systems.
Approach:	They propose a new metric which measures fairness in machine learning models based on the model’s prediction sensitivity to perturbations in input features.
Outcome:	The proposed metric can be linked with a specific notion of group fairness and individual fairness, and correlates well with humans’ perception of fairness.

Canary Extraction in Natural Language Understanding Models (2022.acl-short)

Copied to clipboard

Rahil Parikh, Christophe Dupuy, Rahul Gupta

Robustness in NLP

Challenge:	Recent literature has focused on Model Inversion Attacks (ModIvA) that can extract training data from model parameters.
Approach:	They propose an attack that extracts canaries from NLU training data and reconstructs them using non-sensitive tokens.
Outcome:	The proposed attack can reconstruct a four digit code in the training dataset with a probability of 0.5 in its best configuration.

ARES: Adaptive Red-Teaming and End-to-End Repair of Policy-Reward System (2026.acl-long)

Copied to clipboard

Jiacheng Liang, Yao Ma, Tharindu Kumarage, Satyapriya Krishna, Rahul Gupta, Kai-Wei Chang, Aram Galstyan, Charith Peris

Robustness in NLP

Challenge:	Existing red-teaming approaches focus on policy-level weaknesses, but they overlook systemic weaknesses . aRES exploits dual-targeting weaknesses in both the core LLM and the RM simultaneously.
Approach:	a new framework uncovers weaknesses in both the core and the reward models simultaneously . a "Safety Mentor" generates semantically coherent adversarial prompts .
Outcome:	ARES uncovers weaknesses in both the core LLM and the RM simultaneously . it fine-tunes the LM to detect harmful content, then optimizes the core model .

Toward Informal Language Processing: Knowledge of Slang in Large Language Models (2024.naacl-long)

Copied to clipboard

Zhewei Sun, Qian Hu, Rahul Gupta, Richard Zemel, Yang Xu

Resolving Ambiguities in Text-to-Image Generative Models (2023.acl-long)

Challenge:	Recent advances in large language models (LLMs) have offered a strong potential for natural language systems to process informal language.
Approach:	They propose to use movie subtitles to evaluate slang in large language models . they find that smaller LLMs finetuned on the dataset achieve comparable performance .
Outcome:	The proposed dataset can be used to evaluate LLMs on slang detection and identification of regional and historical sources for interpretive insights.

Copied to clipboard

Ninareh Mehrabi, Palash Goyal, Apurv Verma, Jwala Dhamala, Varun Kumar, Qian Hu, Kai-Wei Chang, Richard Zemel, Aram Galstyan, Rahul Gupta

Multimodality

Challenge:	ambiguities can lead to misinterpretation and miscommunication in natural language . resolving ambiguity is notoriously hard for machines .
Approach:	They propose a framework to disambiguate prompts given to generative models by soliciting clarifications from the end user.
Outcome:	The proposed framework generates more faithful images better aligned with user intention in the presence of ambiguities.

ADePT: Auto-encoder based Differentially Private Text Transformation (2021.eacl-main)

Copied to clipboard

Satyapriya Krishna, Rahul Gupta, Christophe Dupuy

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation (2025.findings-acl)

Challenge:	Differential privacy is an important privacy concern when building statistical models on data containing sensitive information.
Approach:	They propose a utility-preserving differentially private text transformation algorithm using auto-encoders that can be used to transform text to offer robustness against attacks and produce transformations with high semantic quality.
Outcome:	The proposed model performs better against membership inference attacks while offering lower to no degradation in the utility of the underlying transformation process compared to baselines.

Copied to clipboard

Tharindu Kumarage, Ninareh Mehrabi, Anil Ramakrishna, Xinyan Zhao, Richard Zemel, Kai-Wei Chang, Aram Galstyan, Rahul Gupta, Charith Peris

Reasoning

Challenge:	Safety reasoning paradigms require high-quality policy-embedded chain-of-thought datasets . generating such data through human annotations is prohibitively expensive .
Approach:	They propose AIDSAFE: Agentic Iterative Deliberation for Safety Reasoning . AIDS AFE leverages multi-agent deliberation to iteratively expand reasoning on safety policies .
Outcome:	The proposed model improves policy adherence and reasoning quality while maintaining acceptable utility and over-refusal accuracy.

Controlling the Extraction of Memorized Data from Large Language Models via Prompt-Tuning (2023.acl-short)

Copied to clipboard

Mustafa Ozdayi, Charith Peris, Jack FitzGerald, Christophe Dupuy, Jimit Majmudar, Haidar Khan, Rahil Parikh, Rahul Gupta

Towards Realistic Single-Task Continuous Learning Research for NER (2021.findings-emnlp)

Challenge:	Large Language Models memorize significant portions of training data, which poses privacy risk.
Approach:	They propose a prompt-tuning approach to control the extraction rates of memorized content in large language models.
Outcome:	The proposed techniques yield 9.3% increase in extraction rate compared to baseline model . the proposed defense achieves 97.7% reduction with a perplexity increase of 16.9% .

Copied to clipboard

Justin Payan, Yuval Merhav, He Xie, Satyapriya Krishna, Anil Ramakrishna, Mukund Sridhar, Rahul Gupta

Named Entity Recognition

Challenge:	Academic datasets are often static and contain data that is annotated all at once based on fixed annotation guidelines.
Approach:	They propose to build a single-task continuous learning dataset from an existing dataset and release it along with the code to the research community.
Outcome:	The proposed model is based on an existing dataset and released to the research community.

Federated Learning with Noisy User Feedback (2022.naacl-main)

Copied to clipboard

Rahul Sharma, Anil Ramakrishna, Ansel MacLaughlin, Anna Rumshisky, Jimit Majmudar, Clement Chung, Salman Avestimehr, Rahul Gupta

Controlled Data Generation via Insertion Operations for NLU (2022.naacl-industry)

Challenge:	Artificial Intelligence (AI) and Machine Learning (ML) systems are becoming more popular and are causing concerns over user privacy.
Approach:	They propose a method for training ML models using positive and negative user feedback and a framework to extract labels on edge to make FL viable.
Outcome:	The proposed method improves significantly over a self-training baseline, achieving performance closer to models trained with full supervision.

Copied to clipboard

Manoj Kumar, Yuval Merhav, Haidar Khan, Rahul Gupta, Anna Rumshisky, Wael Hamza

Challenge:	a new approach to annotate live traffic is emerging to be cost-effective and efficient . manual data annotation is expensive and not preferred for meeting customer privacy expectations .
Approach:	They propose a targeted synthetic data generation technique by inserting tokens into a given semantic signature.
Outcome:	The proposed approach achieves the same accuracy as training with all available data on a voice assistant dataset.

Improving Large-Scale Conversational Assistants using Model Interpretation based Training Sample Selection (2022.emnlp-industry)

Copied to clipboard

Stefan Schroedl, Manoj Kumar, Kiana Hajebi, Morteza Ziyadi, Sriram Venkatapathy, Anil Ramakrishna, Rahul Gupta, Pradeep Natarajan

Natural Language Interfaces

Challenge:	Large-scale, voice-based conversational assistants process each utterance through a multi-stage pipeline that includes wakeword detection, automatic speech recognition (ASR), natural language understanding (NLU), entity resolution, and textto-speech.
Approach:	They propose a method to identify customer implicitly satisfied with Alexa's responses by leveraging interpretations of model behavior.
Outcome:	The proposed approach produces statistically significant improvements in both offline and online tests.

SWAN: Semantic Watermarking with Abstract Meaning Representation (2026.acl-long)

Copied to clipboard

Ziping Ye, Gourab Dey, Christos Christodoulopoulos, Charith Peris, Anil Ramakrishna, Weitong Ruan, Aram Galstyan, Kai-Wei Chang, Rahul Gupta, Ninareh Mehrabi

Tree-of-Traversals: A Zero-Shot Reasoning Algorithm for Augmenting Black-box Language Models with Knowledge Graphs (2024.acl-long)

Challenge:	Existing methods to embed signatures by adjusting token selection preferences during text generation are highly sensitive to paraphrasing and synonyms.
Approach:	They propose a framework that embeds watermark signatures into the semantic structure of a sentence using Abstract Meaning Representation (AMR).
Outcome:	Empirical evaluation shows SWAN matches state-of-the-art detection performance on unaltered watermarked text while improving robustness against paraphrasing.

Copied to clipboard

Elan Markowitz, Anil Ramakrishna, Jwala Dhamala, Ninareh Mehrabi, Charith Peris, Rahul Gupta, Kai-Wei Chang, Aram Galstyan