Goto

Collaborating Authors

 supporter


An Offline Mobile Conversational Agent for Mental Health Support: Learning from Emotional Dialogues and Psychological Texts with Student-Centered Evaluation

A, Vimaleswar, Sahu, Prabhu Nandan, Sahu, Nilesh Kumar, Lone, Haroon R.

arXiv.org Artificial Intelligence

Mental health plays a crucial role in the overall well-being of an individual. In recent years, digital platforms have increasingly been used to expand mental health and emotional support. However, there are persistent challenges related to limited user accessibility, internet connectivity, and data privacy, which highlight the need for an offline, smartphone-based solutions. To address these challenges, we propose EmoSApp (Emotional Support App): an entirely offline, smartphone-based conversational app designed to provide mental health and emotional support. EmoSApp leverages a language model, specifically the LLaMA-3.2-1B-Instruct, which is fine-tuned and quantized on a custom-curated ``Knowledge Dataset'' comprising 14,582 mental health QA pairs along with multi-turn conversational data, enabling robust domain expertise and fully on-device inference on resource-constrained smartphones. Through qualitative evaluation with students and mental health professionals, we demonstrate that EmoSApp has the ability to respond coherently and empathetically, provide relevant suggestions to user's mental health problems, and maintain interactive dialogue. Additionally, quantitative evaluations on nine commonsense and reasoning benchmarks, along with two mental health specific datasets, demonstrate EmoSApp's effectiveness in low-resource settings. By prioritizing on-device deployment and specialized domain-specific adaptation, EmoSApp serves as a blueprint for future innovations in portable, secure, and highly tailored AI-driven mental health support.


AI chatbots can sway voters' political views, studies say

The Japan Times

AI chatbots can sway voters' political views, studies say Paris - A brief conversation with a partisan AI chatbot can influence voters' political views, studies published Thursday found, with evidence-backed arguments -- true or not -- proving particularly persuasive. Experiments with generative artificial intelligence models, such as OpenAI's GPT-4o and Chinese alternative DeepSeek, found they were able to shift supporters of Republican Donald Trump toward his Democratic opponent Kamala Harris by almost four points on a 100-point scale ahead of the 2024 U.S. presidential election. Opposition supporters in 2025 polls in Canada and Poland meanwhile had their views shifted by up to 10 points after chatting with a bot programmed to persuade. In a time of both misinformation and too much information, quality journalism is more crucial than ever. By subscribing, you can help us get the story right.



Evaluating, Synthesizing, and Enhancing for Customer Support Conversation

Zhu, Jie, Dou, Huaixia, Li, Junhui, Guo, Lifan, Chen, Feng, Zhang, Chi, Kong, Fang

arXiv.org Artificial Intelligence

Effective customer support requires not only accurate problem-solving but also structured and empathetic communication aligned with professional standards. However, existing dialogue datasets often lack strategic guidance, and real-world service data is difficult to access and annotate. To address this, we introduce the task of Customer Support Conversation (CSC), aimed at training customer service supporters to respond using well-defined support strategies. We propose a structured CSC framework grounded in COPC guidelines, defining five conversational stages and twelve strategies to guide high-quality interactions. Based on this, we construct CSConv, an evaluation dataset of 1,855 real-world customer-agent conversations rewritten using LLMs to reflect deliberate strategy use, and annotated accordingly. Additionally, we develop a role-playing approach that simulates strategy-rich conversations using LLM-powered roles aligned with the CSC framework, resulting in the training dataset RoleCS. Experiments show that fine-tuning strong LLMs on RoleCS significantly improves their ability to generate high-quality, strategy-aligned responses on CSConv. Human evaluations further confirm gains in problem resolution.


More than 700 officers to police Villa-Maccabi match

BBC News

Warnings of disruption and protests have come from police as more than 700 officers prepare to mount an operation in Birmingham for Aston Villa's Uefa Europa League match against Maccabi Tel Aviv. Officers will be keeping the public safe and to tackle any crime and disorder on Thursday, West Midlands Police said, with police horses, dogs, the force's drone unit, and road policing officers out in the city. Planned protests include one by supporters of Palestine, who want the match to be called off. Last month, a decision to ban Tel Aviv fans from the event became the focus of parliamentary-level debate . The Israeli club later said supporters would not travel to Birmingham for safety reasons.


On Condorcet's Jury Theorem with Abstention

Meir, Reshef, Ghalme, Ganesh

arXiv.org Artificial Intelligence

The well-known Condorcet Jury Theorem states that, under majority rule, the better of two alternatives is chosen with probability approaching one as the population grows. We study an asymmetric setting where voters face varying participation costs and share a possibly heuristic belief about their pivotality (ability to influence the outcome). In a costly voting setup where voters abstain if their participation cost is greater than their pivotality estimate, we identify a single property of the heuristic belief -- weakly vanishing pivotality -- that gives rise to multiple stable equilibria in which elections are nearly tied. In contrast, strongly vanishing pivotality (as in the standard Calculus of Voting model) yields a unique, trivial equilibrium where only zero-cost voters participate as the population grows. We then characterize when nontrivial equilibria satisfy a version of the Jury Theorem: below a sharp threshold, the majority-preferred candidate wins with probability approaching one; above it, both candidates either win with equal probability.


Larry Ellison overtakes Elon Musk as world's richest person

The Guardian

Larry Ellison, the chair and chief technology officer of Oracle, is a supporter of Donald Trump and has regularly appeared at the White House. Larry Ellison, the chair and chief technology officer of Oracle, is a supporter of Donald Trump and has regularly appeared at the White House. Oracle co-founder's shares rose by 40% in early trading, valuing his fortune at $393bn, just ahead of Musk's $384bn US tech billionaire Larry Ellison is neck-and-neck with Elon Musk in the contest to be the world's richest person after briefly overtaking the Tesla chief executive on Wednesday Ellison's wealth surged after Oracle, the business software company in which he owns a stake of 41%, reported better than expected financial results. Oracle shares rose by more than 40% in early trading, at one point valuing the business software company at approximately $960bn (£707bn) and Ellison's stake at $393bn, just ahead of Musk's fortune of $384bn, according to Bloomberg's billionaires index. However, Ellison's lead was short-lived as the stock closed at $328, a rise of 36% valuing Ellison's shareholding at $378bn and putting Musk back ahead.


Convert Language Model into a Value-based Strategic Planner

Wang, Xiaoyu, Zhao, Yue, Gu, Qingqing, Jiang, Zhonglin, Chen, Xiaokai, Chen, Yong, Ji, Luo

arXiv.org Artificial Intelligence

Emotional support conversation (ESC) aims to alleviate the emotional distress of individuals through effective conversations. Although large language models (LLMs) have obtained remarkable progress on ESC, most of these studies might not define the diagram from the state model perspective, therefore providing a suboptimal solution for long-term satisfaction. To address such an issue, we leverage the Q-learning on LLMs, and propose a framework called straQ*. Our framework allows a plug-and-play LLM to bootstrap the planning during ESC, determine the optimal strategy based on long-term returns, and finally guide the LLM to response. Substantial experiments on ESC datasets suggest that straQ* outperforms many baselines, including direct inference, self-refine, chain of thought, finetuning, and finite state machines.



Chabria: 3 things that should scare us about Trump's fake video of Obama

Los Angeles Times

On Sunday, our thoughtful and reserved president reposted on his Truth Social site a video generated by artificial intelligence that falsely showed former President Obama being arrested and imprisoned. There are those among you who think this is high humor; those among you who who find it as tiresome as it is offensive; and those among you blissfully unaware of the mental morass that is Truth Social. Whatever camp you fall into, the video crosses all demographics by being expected -- just another crazy Trump stunt in a repetitive cycle of division and diversion so frequent it makes Groundhog Day seem fresh. But there are three reasons why this particular video -- not made by the president but amplified to thousands -- is worth noting, and maybe even worth fearing. First, it is flat-out racist. In it, Obama is ripped out of a chair in the Oval Office and forced onto his knees, almost bowing, to a laughing Trump.