arXiv subjects

Navya Jain

Publications and source records attributed to Navya Jain.

4 recordsLinked to original sources

arXiv2024

Bias Amplification: Large Language Models as Increasingly Biased Media

Model collapse, a phenomenon characterized by performance degradation due to iterative training on synthetic data, has been widely studied. However, its implications for bias amplification, the progressive intensification of pre-existing societal biases in Large Language Models (LLMs), remain significantly underexplored, despite the growing influence of LLMs in shaping online discourse. In this paper, we introduce a open, generational, and long-context benchmark specifically designed to measure political bias amplification in LLMs, leveraging sentence continuation tasks derived from a comprehensive dataset of U.S. political news. Our empirical study using GPT-2 reveals consistent and substantial political bias intensification (e.g., right-leaning amplification) over iterative synthetic training cycles. We evaluate three mitigation strategies, Overfitting, Preservation, and Accumulation, and demonstrate that bias amplification persists independently of model collapse, even when the latter is effectively controlled. Furthermore, we propose a mechanistic analysis approach that identifies neurons correlated with specific phenomena during inference through regression and statistical tests. This analysis uncovers largely distinct neuron populations driving bias amplification and model collapse, underscoring fundamentally different underlying mechanisms. Finally, we supplement our empirical findings with theoretical intuition that explains the separate origins of these phenomena, guiding targeted strategies for bias mitigation.

cs.AI↗

arXiv2024

From Text to Emoji: How PEFT-Driven Personality Manipulation Unleashes the Emoji Potential in LLMs

The manipulation of the personality traits of large language models (LLMs) has emerged as a key area of research. Methods like prompt-based In-Context Knowledge Editing (IKE) and gradient-based Model Editor Networks (MEND) have been explored but show irregularity and variability; IKE depends on the prompt, leading to variability and sensitivity, while MEND yields inconsistent and gibberish outputs. To address this, we employed Opinion QA Based Parameter-Efficient Fine-Tuning (PEFT), specifically Quantized Low-Rank Adaptation (QLoRA), to manipulate the Big Five personality traits: Openness, Conscientiousness, Extraversion, Agreeableness, and Neuroticism. After PEFT, models such as Mistral-7B-Instruct and LLaMA-2-7B-chat showed a latent behaviour by generating emojis for certain traits, despite no emojis being present in the PEFT data. For instance, LLaMA-2-7B-chat generated emojis in 99.5\% of extraversion-related test instances, while Mistral-7B-Instruct did so in 92.5\% of openness-related test instances. ICL Explainability analysis indicated that the LLMs used emojis intentionally to express these traits. Mechanistic Interpretability analysis showed that this latent behaviour of LLMs could be traced to specific neurons that became activated or amplified after PEFT. This paper provides a number of novel contributions. First, introducing an Opinion QA dataset for PEFT-driven personality manipulation; second, developing metric models to benchmark LLM personality traits; third, demonstrating PEFT's superiority over IKE in personality manipulation; and finally, analysing and validating emoji usage through explainability methods such as Mechanistic Interpretability and In-context learning Explainability methods.

cs.CL↗

arXiv2024

Can LLMs Help Predict Elections? (Counter)Evidence from the World's Largest Democracy

The study of how social media affects the formation of public opinion and its influence on political results has been a popular field of inquiry. However, current approaches frequently offer a limited comprehension of the complex political phenomena, yielding inconsistent outcomes. In this work, we introduce a new method: harnessing the capabilities of Large Language Models (LLMs) to examine social media data and forecast election outcomes. Our research diverges from traditional methodologies in two crucial respects. First, we utilize the sophisticated capabilities of foundational LLMs, which can comprehend the complex linguistic subtleties and contextual details present in social media data. Second, we focus on data from X (Twitter) in India to predict state assembly election outcomes. Our method entails sentiment analysis of election-related tweets through LLMs to forecast the actual election results, and we demonstrate the superiority of our LLM-based method against more traditional exit and opinion polls. Overall, our research offers valuable insights into the unique dynamics of Indian politics and the remarkable impact of social media in molding public attitudes within this context.

cs.SI↗

arXiv2021

Detecting Blurred Ground-based Sky/Cloud Images

Ground-based whole sky imagers (WSIs) are being used by researchers in various fields to study the atmospheric events. These ground-based sky cameras capture visible-light images of the sky at regular intervals of time. Owing to the atmospheric interference and camera sensor noise, the captured images often exhibit noise and blur. This may pose a problem in subsequent image processing stages. Therefore, it is important to accurately identify the blurred images. This is a difficult task, as clouds have varying shapes, textures, and soft edges whereas the sky acts as a homogeneous and uniform background. In this paper, we propose an efficient framework that can identify the blurred sky/cloud images. Using a static external marker, our proposed methodology has a detection accuracy of 94\%. To the best of our knowledge, our approach is the first of its kind in the automatic identification of blurred images for ground-based sky/cloud images.

cs.CV↗