arXiv subjects

Avneet Kaur

Publications and source records attributed to Avneet Kaur.

7 recordsLinked to original sources

arXiv2025

Echoes of Agreement: Argument Driven Opinion Shifts in Large Language Models

There have been numerous studies evaluating bias of LLMs towards political topics. However, how positions towards these topics in model outputs are highly sensitive to the prompt. What happens when the prompt itself is suggestive of certain arguments towards those positions remains underexplored. This is crucial for understanding how robust these bias evaluations are and for understanding model behaviour, as these models frequently interact with opinionated text. To that end, we conduct experiments for political bias evaluation in presence of supporting and refuting arguments. Our experiments show that such arguments substantially alter model responses towards the direction of the provided argument in both single-turn and multi-turn settings. Moreover, we find that the strength of these arguments influences the directional agreement rate of model responses. These effects point to a sycophantic tendency in LLMs adapting their stance to align with the presented arguments which has downstream implications for measuring political bias and developing effective mitigation strategies.

cs.CL↗

arXiv2025

Beyond the Battlefield: Framing Analysis of Media Coverage in Conflict Reporting

Framing used by news media, especially in times of conflict, can have substantial impact on readers' opinion, potentially aggravating the conflict itself. Current studies on the topic of conflict framing have limited insights due to their qualitative nature or only look at surface level generic frames without going deeper. In this work, we identify indicators of war and peace journalism, as outlined by prior work in conflict studies, in a corpus of news articles reporting on the Israel-Palestine war. For our analysis, we use computational approaches, using a combination of frame semantics and large language models to identify both communicative framing and its connection to linguistic framing. Our analysis reveals a higher focus on war based reporting rather than peace based. We also show substantial differences in reporting across the US, UK, and Middle Eastern news outlets in framing who the assailant and victims of the conflict are, surfacing biases within the media.

cs.CL↗

arXiv2025

State estimator design using Jordan based long short-term memory networks

State estimation of a dynamical system refers to estimating the state of a system given an imperfect model, noisy measurements and some or no information about the initial state. While Kalman filtering is optimal for estimation of linear systems with Gaussian noises, calculation of optimal estimators for nonlinear systems is challenging. We focus on establishing a pathway to optimal estimation of high-order systems by using recurrent connections motivated by Jordan recurrent neural networks(JRNs). The results are compared to the corresponding Elman structure based long short-term memory network(ELSTM) and the KF for linear and EKF for nonlinear systems. The results suggest that for nonlinear systems, the use of long short-term memory networks can improve estimation error and also computation time. Also, the Jordan based long short-term memory networks(JLSTMs) require less training to achieve performance similar to ELSTMs.

math.OC↗

arXiv2025

Stability of Jordan Recurrent Neural Network Estimator

State estimation refers to determining the states of a dynamical system that starts from a noisy initial condition and evolves under process noise, based on noisy measurements and a known system model. For linear dynamical systems with white Gaussian noises of known mean and variance, Kalman filtering is a well-known method that leads to stable error dynamics for detectable systems. There are some non-optimal extensions to nonlinear systems. Recent work has used neural networks to develop estimators for nonlinear systems that optimize a criterion. Stability of the error dynamics is even more important than optimality. Jordan recurrent neural networks (JRNs) have a structure that mimics that of a dynamical system and are thus appealing for estimator design. We show that a JRN performs better than an extended Kalman filter(EKF) and unscented Kalman filter(UKF) for several examples. The main contribution of this paper is an input-to-state stability analysis of the error dynamics of JRNs. The stability of the error dynamics of several examples is shown.

math.OC↗

arXiv2024

The impact of fear and behaviour response to established and novel diseases

We analyze a disease transmission model that allows individuals to acquire fear and change their behaviour to reduce transmission. Fear is acquired through contact with infected individuals and through the influence of fearful individuals. We analyze the model in two limits: First, an Established Disease Limit (EDL), where the spread of the disease is much faster than the spread of fear, and second, a Novel Disease Limit (NDL), where the spread of the disease is comparable to that of fear. For the EDL, we show that the relative rate of fear acquisition to disease transmission controls the size of the fearful population at the end of a disease outbreak, and that the fear-induced contact reduction behaviour has very little impact on disease burden. Conversely, we show that in the NDL, disease burden can be controlled by fear-induced behaviour depending on the rate of fear loss. Specifically, fear-induced behaviour introduces a contact parameter $p$, which if too large prevents the contact reduction from effectively managing the epidemic. We analytically identify a critical prophylactic behaviour parameter $p=p_c$ where this happens leading to a discontinuity in epidemic prevalence. We show that this change in disease burden introduces delayed epidemic waves.

physics.soc-ph↗

arXiv2019

Pneumothorax Segmentation: Deep Learning Image Segmentation to predict Pneumothorax

Computer vision has shown promising results in medical image processing. Pneumothorax is a deadly condition and if not diagnosed and treated at time then it causes death. It can be diagnosed with chest X-ray images. We need an expert and experienced radiologist to predict whether a person is suffering from pneumothorax or not by looking at the chest X-ray images. Everyone does not have access to such a facility. Moreover, in some cases, we need quick diagnoses. So we propose an image segmentation model to predict and give the output a mask that will assist the doctor in taking this crucial decision. Deep Learning has proved their worth in many areas and outperformed man state-of-the-art models. We want to use the power of these deep learning model to solve this problem. We have used U-net [13] architecture with ResNet [17] as a backbone and achieved promising results. U-net [13] performs very well in medical image processing and semantic segmentation. Our problem falls in the semantic segmentation category.

cs.CV↗

arXiv2018

Tell Me Why Is It So? Explaining Knowledge Graph Relationships by Finding Descriptive Support Passages

We address the problem of finding descriptive explanations of facts stored in a knowledge graph. This is important in high-risk domains such as healthcare, intelligence, etc. where users need additional information for decision making and is especially crucial for applications that rely on automatically constructed knowledge bases where machine learned systems extract facts from an input corpus and working of the extractors is opaque to the end-user. We follow an approach inspired from information retrieval and propose a simple and efficient, yet effective solution that takes into account passage level as well as document level properties to produce a ranked list of passages describing a given input relation. We test our approach using Wikidata as the knowledge base and Wikipedia as the source corpus and report results of user studies conducted to study the effectiveness of our proposed model.

cs.AI↗