Machine Translation (MT) is undergoing a paradigm shift, with systems based on fine-tuned large language models (LLM) becoming increasingly competitive with traditional encoder-decoder models trained specifically for translation tasks. However, LLM-based systems are at a higher risk of generating hallucinations, which can severely undermine user's trust and safety. Most prior research on hallucination mitigation focuses on traditional MT models, with solutions that involve post-hoc mitigation - detecting hallucinated translations and re-translating them. While effective, this approach introduces additional complexity in deploying extra tools in production and also increases latency. To address these limitations, we propose a method that intrinsically learns to mitigate hallucinations during the model training phase. Specifically, we introduce a data creation framework to generate hallucination focused preference datasets. Fine-tuning LLMs on these preference datasets reduces the hallucination rate by an average of 96% across five language pairs, while preserving overall translation quality. In a zero-shot setting our approach reduces hallucinations by 89% on an average across three unseen target languages.

Large Language Models (LLMs) are becoming increasingly persuasive, demonstrating the ability to personalize arguments in conversation with humans by leveraging their personal data. This may have serious impacts on the scale and effectiveness of disinformation campaigns. We studied the persuasiveness of LLMs in a debate setting by having humans $(n=33)$ engage with LLM-generated arguments intended to change the human's opinion. We quantified the LLM's effect by measuring human agreement with the debate's hypothesis pre- and post-debate and analyzing both the magnitude of opinion change, as well as the likelihood of an update in the LLM's direction. We compare persuasiveness across established persuasion strategies, including personalized arguments informed by user demographics and personality, appeal to fabricated statistics, and a mixed strategy utilizing both personalized arguments and fabricated statistics. We found that static arguments generated by humans and GPT-4o-mini have comparable persuasive power. However, the LLM outperformed static human-written arguments when leveraging the mixed strategy in an interactive debate setting. This approach had a $\mathbf{51\%}$ chance of persuading participants to modify their initial position, compared to $\mathbf{32\%}$ for the static human-written arguments. Our results highlight the concerning potential for LLMs to enable inexpensive and persuasive large-scale disinformation campaigns.

An LLM is stable if it reaches the same conclusion when asked the identical question multiple times. We find leading LLMs like gpt-4o, claude-3.5, and gemini-1.5 are unstable when providing answers to hard legal questions, even when made as deterministic as possible by setting temperature to 0. We curate and release a novel dataset of 500 legal questions distilled from real cases, involving two parties, with facts, competing legal arguments, and the question of which party should prevail. When provided the exact same question, we observe that LLMs sometimes say one party should win, while other times saying the other party should win. This instability has implications for the increasing numbers of legal AI products, legal processes, and lawyers relying on these LLMs.

This study explores a novel approach to advancing dementia care by integrating socially assistive robotics, reinforcement learning (RL), large language models (LLMs), and clinical domain expertise within a simulated environment. This integration addresses the critical challenge of limited experimental data in socially assistive robotics for dementia care, providing a dynamic simulation environment that realistically models interactions between persons living with dementia (PLWDs) and robotic caregivers. The proposed framework introduces a probabilistic model to represent the cognitive and emotional states of PLWDs, combined with an LLM-based behavior simulation to emulate their responses. We further develop and train an adaptive RL system enabling humanoid robots, such as Pepper, to deliver context-aware and personalized interactions and assistance based on PLWDs' cognitive and emotional states. The framework also generalizes to computer-based agents, highlighting its versatility. Results demonstrate that the RL system, enhanced by LLMs, effectively interprets and responds to the complex needs of PLWDs, providing tailored caregiving strategies. This research contributes to human-computer and human-robot interaction by offering a customizable AI-driven caregiving platform, advancing understanding of dementia-related challenges, and fostering collaborative innovation in assistive technologies. The proposed approach has the potential to enhance the independence and quality of life for PLWDs while alleviating caregiver burden, underscoring the transformative role of interaction-focused AI systems in dementia care.

Vision-Language Models (VLMs) have achieved remarkable success across a range of multimodal tasks; however, their practical deployment is often constrained by high computational costs and prolonged inference times. Since the vision modality typically carries more information than the text modality, compressing visual prompts offers a promising solution to alleviate these challenges. Existing approaches predominantly focus on refining model architectures or directly reducing the number of visual tokens. However, these methods often compromise inference performance due to a lack of consideration for the unique spatial and temporal characteristics of visual data. In this work, we propose a token compression paradigm that operates on both spatial and temporal dimensions. Our approach includes a learning-free, plug-and-play compression pipeline that can be seamlessly integrated into most Multimodal Large Language Model (MLLM) frameworks. By leveraging this method, we enhance the model inference capability while simultaneously reducing its computational cost. Experimental results on the Video-QA task demonstrate the effectiveness of the proposed approach, showcasing significant improvements in efficiency without sacrificing performance.

This study investigates the dissemination of disinformation on social media platforms during the DANA event (DANA is a Spanish acronym for Depresion Aislada en Niveles Altos, translating to high-altitude isolated depression) that resulted in extremely heavy rainfall and devastating floods in Valencia, Spain, on October 29, 2024. We created a novel dataset of 650 TikTok and X posts, which was manually annotated to differentiate between disinformation and trustworthy content. Additionally, a Few-Shot annotation approach with GPT-4o achieved substantial agreement (Cohen's kappa of 0.684) with manual labels. Emotion analysis revealed that disinformation on X is mainly associated with increased sadness and fear, while on TikTok, it correlates with higher levels of anger and disgust. Linguistic analysis using the LIWC dictionary showed that trustworthy content utilizes more articulate and factual language, whereas disinformation employs negations, perceptual words, and personal anecdotes to appear credible. Audio analysis of TikTok posts highlighted distinct patterns: trustworthy audios featured brighter tones and robotic or monotone narration, promoting clarity and credibility, while disinformation audios leveraged tonal variation, emotional depth, and manipulative musical elements to amplify engagement. In detection models, SVM+TF-IDF achieved the highest F1-Score, excelling with limited data. Incorporating audio features into roberta-large-bne improved both Accuracy and F1-Score, surpassing its text-only counterpart and SVM in Accuracy. GPT-4o Few-Shot also performed well, showcasing the potential of large language models for automated disinformation detection. These findings demonstrate the importance of leveraging both textual and audio features for improved disinformation detection on multimodal platforms like TikTok.

The first Natural Office Talkers in Settings of Far-field Audio Recordings (NOTSOFAR-1) Challenge is a pivotal initiative that sets new benchmarks by offering datasets more representative of the needs of real-world business applications than those previously available. The challenge provides a unique combination of 280 recorded meetings across 30 diverse environments, capturing real-world acoustic conditions and conversational dynamics, and a 1000-hour simulated training dataset, synthesized with enhanced authenticity for real-world generalization, incorporating 15,000 real acoustic transfer functions. In this paper, we provide an overview of the systems submitted to the challenge and analyze the top-performing approaches, hypothesizing the factors behind their success. Additionally, we highlight promising directions left unexplored by participants. By presenting key findings and actionable insights, this work aims to drive further innovation and progress in DASR research and applications.

Contextually Entangled Gradient Mapping (CEGM) introduces a new approach to gradient optimization, redefining the relationship between contextual embeddings and gradient updates to enhance semantic coherence and reasoning capabilities in neural architectures. By treating gradients as dynamic carriers of contextual dependencies rather than isolated numerical entities, the proposed methodology bridges critical gaps in existing optimization strategies. The integration of entangled gradient dynamics into a loss regularization framework demonstrated significant improvements in tasks involving long-form reasoning, contextual retention, and adaptability to unseen domains. Experimental evaluations showed that the CEGM-enhanced model consistently outperformed baseline approaches, achieving higher accuracy in token-level predictions and greater resilience to noisy inputs. Practical implementations involved modifications to training pipelines, introducing entanglement layers and dynamic coefficient adjustments that seamlessly align with existing architectures. Results further highlighted reductions in semantic drift during sequential transformations and improvements in embedding coherence across paraphrased sentences, showing the robustness and versatility of the proposed methodology. The findings demonstrate the broader implications of gradient entanglement for both theoretical advancements and practical applications in optimization strategies.

This paper introduces a continuous-time stochastic dynamical framework for understanding how large language models (LLMs) may self-amplify latent biases or toxicity through their own chain-of-thought reasoning. The model posits an instantaneous "severity" variable $x(t) \in [0,1]$ evolving under a stochastic differential equation (SDE) with a drift term $\mu(x)$ and diffusion $\sigma(x)$. Crucially, such a process can be consistently analyzed via the Fokker--Planck approach if each incremental step behaves nearly Markovian in severity space. The analysis investigates critical phenomena, showing that certain parameter regimes create phase transitions from subcritical (self-correcting) to supercritical (runaway severity). The paper derives stationary distributions, first-passage times to harmful thresholds, and scaling laws near critical points. Finally, it highlights implications for agents and extended LLM reasoning models: in principle, these equations might serve as a basis for formal verification of whether a model remains stable or propagates bias over repeated inferences.

Large Language Models (LLMs) have shown remarkable advancements but also raise concerns about cultural bias, often reflecting dominant narratives at the expense of under-represented subcultures. In this study, we evaluate the capacity of LLMs to recognize and accurately respond to the Little Traditions within Indian society, encompassing localized cultural practices and subcultures such as caste, kinship, marriage, and religion. Through a series of case studies, we assess whether LLMs can balance the interplay between dominant Great Traditions and localized Little Traditions. We explore various prompting strategies and further investigate whether using prompts in regional languages enhances the models cultural sensitivity and response quality. Our findings reveal that while LLMs demonstrate an ability to articulate cultural nuances, they often struggle to apply this understanding in practical, context-specific scenarios. To the best of our knowledge, this is the first study to analyze LLMs engagement with Indian subcultures, offering critical insights into the challenges of embedding cultural diversity in AI systems.