ABAmrita Bhattacharjee

Amrita Bhattacharjee

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Amrita Bhattacharjee has a total of 20 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Can Typos Cause Harm? The Impact of Imperfect Input on LLM Safety

    by Saurabh Zinjad, Amrita Bhattacharjee, Alimohammad Beigi, Huan Liu

  • Open Access

    SafeSteer: Interpretable Safety Steering with Refusal-Evasion in LLMs

    by Shaona Ghosh, Amrita Bhattacharjee, Yftah Ziser, Christopher Parisien

    Fine-tuning large language models (LLMs) to adapt to evolving safety policies is costly and impractical. Mechanistic interpretability enables inference-time control through latent activation steering, yet its potential for precise, customizable safety adjustments remains largely untapped. This paper investigates an approach called SafeSteer for guiding the outputs of LLMs by: (i) leveraging category-specific steering vectors for more precise control, (ii) employing a simple, gradient-free unsupervised method to enhance safety steering while preserving text quality, topic relevance, and without explicit refusal, and (iii) accomplishing this without a hard requirement of contrastive pairwise safe data. We also highlight that our method, being simple and effective, aligns with recent studies suggesting that simple techniques often outperform more complex ones in activation steering. We showcase the effectiveness of our approach across various LLMs, datasets, and risk categories, demonstrating its ability to provide precise control, prevent blanket refusals, and guide models toward generating safe content while maintaining topic relevance.

  • Open Access

    A Simple Yet Effective Method for Non-Refusing Context Relevant Fine-grained Safety Steering in LLMs

    by Shaona Ghosh, Amrita Bhattacharjee, Yftah Ziser, Christopher Parisien

    Shaona Ghosh, Amrita Bhattacharjee, Yftah Ziser, Christopher Parisien. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.


  • Open Access

    Do LLMs Understand Ambiguity in Text? A Case Study in Open-world Question Answering

    by Aryan Keluskar, Amrita Bhattacharjee, Huan Liu

    Ambiguity in natural language poses significant challenges to Large Language Models (LLMs) used for open-domain question answering. LLMs often struggle with the inherent uncertainties of human communication, leading to misinterpretations, miscommunications, hallucinations, and biased responses. This significantly weakens their ability to be used for tasks like fact-checking, question answering, feature extraction, and sentiment analysis. Using open-domain question answering as a test case, we compare off-the-shelf and few-shot LLM performance, focusing on measuring the impact of explicit disambiguation strategies. We demonstrate how simple, training-free, token-level disambiguation methods may be effectively used to improve LLM performance for ambiguous question answering tasks. We empirically show our findings and discuss best practices and broader impacts regarding ambiguity in LLMs.


  • Open Access

    Towards Inference-time Category-wise Safety Steering for Large Language Models

    by Amrita Bhattacharjee, Shaona Ghosh, Traian Rebedea, Christopher Parisien

    While large language models (LLMs) have seen unprecedented advancements in capabilities and applications across a variety of use-cases, safety alignment of these models is still an area of active research. The fragile nature of LLMs, even models that have undergone extensive alignment and safety training regimes, warrants additional safety steering steps via training-free, inference-time methods. While recent work in the area of mechanistic interpretability has investigated how activations in latent representation spaces may encode concepts, and thereafter performed representation engineering to induce such concepts in LLM outputs, the applicability of such for safety is relatively under-explored. Unlike recent inference-time safety steering works, in this paper we explore safety steering of LLM outputs using: (i) category-specific steering vectors, thereby enabling fine-grained control over the steering, and (ii) sophisticated methods for extracting informative steering vectors for more effective safety steering while retaining quality of the generated text. We demonstrate our exploration on multiple LLMs and datasets, and showcase the effectiveness of the proposed steering method, along with a discussion on the implications and best practices.

  • Open Access

    ResumeFlow: An LLM-facilitated Pipeline for Personalized Resume Generation and Refinement

    by Saurabh Bhausaheb Zinjad, Amrita Bhattacharjee, Amey Bhilegaonkar, Huan Liu

    Crafting the ideal, job-specific resume is a challenging task for many job applicants, especially for early-career applicants. While it is highly recommended that applicants tailor their resume to the specific role they are applying for, manually tailoring resumes to job descriptions and role-specific requirements is often (1) extremely time-consuming, and (2) prone to human errors. Furthermore, performing such a tailoring step at scale while applying to several roles may result in a lack of quality of the edited resumes. To tackle this problem, in this demo paper, we propose ResumeFlow: a Large Language Model (LLM) aided tool that enables an end user to simply provide their detailed resume and the desired job posting, and obtain a personalized resume specifically tailored to that specific job posting in the matter of a few seconds. Our proposed pipeline leverages the language understanding and information extraction capabilities of state-of-the-art LLMs such as OpenAI's GPT-4 and Google's Gemini, in order to (1) extract details from a job description, (2) extract role-specific details from the user-provided resume, and then (3) use these to refine and generate a role-specific resume for the user. Our easy-to-use tool leverages the user-chosen LLM in a completely off-the-shelf manner, thus requiring no fine-tuning. We demonstrate the effectiveness of our tool via a https://www.youtube.com/watch?v=Agl7ugyu1N4 and propose novel task-specific evaluation metrics to control for alignment and hallucination. Our tool is available at https://job-aligned-resume.streamlit.app.


  • Adversarial Text Purification: A Large Language Model Approach for Defense

    by Raha Moraffah, Shubh Khandelwal, Amrita Bhattacharjee, Huan Liu


  • Open Access

    Fighting Fire with Fire: Can ChatGPT Detect AI-generated Text?

    by Amrita Bhattacharjee, Huan Liu

    Large language models (LLMs) such as ChatGPT are increasingly being used for various use cases, including text content generation at scale. Although detection methods for such AI-generated text exist already, we investigate ChatGPT's performance as a detector on such AI-generated text, inspired by works that use ChatGPT as a data labeler or annotator. We evaluate the zero-shot performance of ChatGPT in the task of human-written vs. AI-generated text detection, and perform experiments on publicly available datasets. We empirically investigate if ChatGPT is symmetrically effective in detecting AI-generated or human-written text. Our findings provide insight on how ChatGPT and similar LLMs may be leveraged in automated detection pipelines by simply focusing on solving a specific aspect of the problem and deriving the rest from that solution. All code and data is available at https://github.com/AmritaBh/ChatGPT-as-Detector.


  • Open Access

    Towards Detecting Harmful Agendas in News Articles

    by Melanie Subbiah, Amrita Bhattacharjee, Yilun Hua, Tharindu Kumarage, Huan Liu, Kathleen McKeown

    Manipulated news online is a growing problem which necessitates the use of automated systems to curtail its spread. We argue that while misinformation and disinformation detection have been studied, there has been a lack of investment in the important open challenge of detecting harmful agendas in news articles; identifying harmful agendas is critical to flag news campaigns with the greatest potential for real world harm. Moreover, due to real concerns around censorship, harmful agenda detectors must be interpretable to be effective. In this work, we propose this new task and release a dataset, NewsAgendas, of annotated news articles for agenda identification. We show how interpretable systems can be effective on this task and demonstrate that they can perform comparably to black-box models.

  • Open Access

    Towards Detecting Harmful Agendas in News Articles

    by Melanie Subbiah, Amrita Bhattacharjee, Yilun Hua, Tharindu Kumarage, Huan Liu, Kathleen McKeown

    Melanie Subbiah, Amrita Bhattacharjee, Yilun Hua, Tharindu Kumarage, Huan Liu, Kathleen McKeown. Proceedings of the 13th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis. 2023.