Large language models interact with users through a simulated 'Assistant' persona. While the Assistant is typically trained to be helpful, harmless, and honest, it sometimes deviates from these ideals. In this paper, we identify directions in the model's activation space-persona vectors-underlying several traits, such as evil, sycophancy, and propensity to hallucinate. We confirm that these vectors can be used to monitor fluctuations in the Assistant's personality at deployment time. We then apply persona vectors to predict and control personality shifts that occur during training. We find that both intended and unintended personality changes after finetuning are strongly correlated with shifts along the relevant persona vectors. These shifts can be mitigated through post-hoc intervention, or avoided in the first place with a new preventative steering method. Moreover, persona vectors can be used to flag training data that will produce undesirable personality changes, both at the dataset level and the individual sample level. Our method for extracting persona vectors is automated and can be applied to any personality trait of interest, given only a natural-language description.

Pretrained multilingual models exhibit the same social bias as models processing English texts. This systematic review analyzes emerging research that extends bias evaluation and mitigation approaches into multilingual and non-English contexts. We examine these studies with respect to linguistic diversity, cultural awareness, and their choice of evaluation metrics and mitigation techniques. Our survey illuminates gaps in the field's dominant methodological design choices (e.g., preference for certain languages, scarcity of multilingual mitigation experiments) while cataloging common issues encountered and solutions implemented in adapting bias benchmarks across languages and cultures. Drawing from the implications of our findings, we chart directions for future research that can reinforce the multilingual bias literature's inclusivity, cross-cultural appropriateness, and alignment with state-of-the-art NLP advancements.

When the chief executive of the Financial Times suggested at a media conference this summer that rival publishers might consider a "Nato for news" alliance to strengthen negotiations with artificial intelligence companies there was a ripple of chuckles from attendees. Yet Jon Slade's revelation that his website had seen a "pretty sudden and sustained" decline of 25% to 30% in traffic to its articles from readers arriving via internet search engines quickly made clear the serious nature of the threat the AI revolution poses. Queries typed into sites such as Google, which accounts for more than 90% of the search market, have been central to online journalism since its inception, with news providers optimising headlines and content to ensure a top ranking and revenue-raising clicks. But now Google's AI Overviews, which sit at the top of the results page and summarise responses and often negate the need to follow links to content, as well as its recently launched AI Mode tab that answers queries in a chatbot format, have prompted fears of a "Google zero" future where traffic referrals dry up. "This is the single biggest change to search I have seen in decades," says one senior editorial tech executive.

The artificial intelligence company Anthropic has agreed to pay 1.5bn to settle a class-action lawsuit by book authors who say the company took pirated copies of their works to train its chatbot. The company has agreed to pay authors about 3,000 for each of an estimated 500,000 books covered by the settlement. "It is the first of its kind in the AI era." A trio of authors – thriller novelist Andrea Bartz and nonfiction writers Charles Graeber and Kirk Wallace Johnson – sued last year and now represent a broader group of writers and publishers whose books Anthropic downloaded to train its chatbot Claude. If Anthropic had not settled, experts say losing the case after a scheduled December trial could have cost the San Francisco-based company even more money.

The amount is well below what Anthropic may have had to pay if it had lost the case at trial. Experts said the plaintiffs may have been awarded at least billions of dollars in damages, with some estimates placing the total figure over 1 trillion. It is the first of its kind in the AI era. Anthropic is not admitting any wrongdoing or liability. "Today's settlement, if approved, will resolve the plaintiffs' remaining legacy claims. We remain committed to developing safe AI systems that help people and organizations extend their capabilities, advance scientific discovery, and solve complex problems," Anthropic deputy general counsel Aparna Sridhar said in a statement.

The governing board for the electric carmaker Tesla has put forward a pay package for CEO Elon Musk that could make him the world's first trillionaire -- but only if he meets a series of high-performance standards over the next 10 years. The proposal became public on Friday, as part of the company's regulatory filings. Musk is already considered one of the world's wealthiest businessmen, and one of his eye-popping pay packages from 2018 continues to be the subject of a legal battle. But if approved, the latest proposal would likely be the largest corporate pay package in United States history. Tesla shareholders will vote on the compensation scheme on November 6.

The development of Long-CoT reasoning has advanced LLM performance across various tasks, including language understanding, complex problem solving, and code generation. This paradigm enables models to generate intermediate reasoning steps, thereby improving both accuracy and interpretability. However, despite these advancements, a comprehensive understanding of how CoT-based reasoning affects the trustworthiness of language models remains underdeveloped. In this paper, we survey recent work on reasoning models and CoT techniques, focusing on five core dimensions of trustworthy reasoning: truthfulness, safety, robustness, fairness, and privacy. For each aspect, we provide a clear and structured overview of recent studies in chronological order, along with detailed analyses of their methodologies, findings, and limitations. Future research directions are also appended at the end for reference and discussion. Overall, while reasoning techniques hold promise for enhancing model trustworthiness through hallucination mitigation, harmful content detection, and robustness improvement, cutting-edge reasoning models themselves often suffer from comparable or even greater vulnerabilities in safety, robustness, and privacy. By synthesizing these insights, we hope this work serves as a valuable and timely resource for the AI safety community to stay informed on the latest progress in reasoning trustworthiness. A full list of related papers can be found at \href{https://github.com/ybwang119/Awesome-reasoning-safety}{https://github.com/ybwang119/Awesome-reasoning-safety}.

Understanding the complexities of judicial deliberation is crucial for assessing the efficacy and fairness of a justice system. However, empirical studies of judicial panels are constrained by significant ethical and practical barriers. This paper introduces SAMVAD, an innovative Multi-Agent System (MAS) designed to simulate the deliberation process within the framework of the Indian justice system. Our system comprises agents representing key judicial roles: a Judge, a Prosecution Counsel, a Defense Counsel, and multiple Adjudicators (simulating a judicial bench), all powered by large language models (LLMs). A primary contribution of this work is the integration of Retrieval-Augmented Generation (RAG), grounded in a domain-specific knowledge base of landmark Indian legal documents, including the Indian Penal Code and the Constitution of India. This RAG functionality enables the Judge and Counsel agents to generate legally sound instructions and arguments, complete with source citations, thereby enhancing both the fidelity and transparency of the simulation. The Adjudicator agents engage in iterative deliberation rounds, processing case facts, legal instructions, and arguments to reach a consensus-based verdict. We detail the system architecture, agent communication protocols, the RAG pipeline, the simulation workflow, and a comprehensive evaluation plan designed to assess performance, deliberation quality, and outcome consistency. This work provides a configurable and explainable MAS platform for exploring legal reasoning and group decision-making dynamics in judicial simulations, specifically tailored to the Indian legal context and augmented with verifiable legal grounding via RAG.

--Optical Character Recognition (OCR) in multilingual, noisy, and diverse real-world images remains a significant challenge for optical character recognition systems. With the rise of Large Vision-Language Models (L VLMs), there is growing interest in their ability to generalize and reason beyond fixed OCR pipelines. In this work, we introduce Sprinklr-Edge-OCR, a novel OCR system built specifically optimized for edge deployment in resource-constrained environments. We present a large-scale comparative evaluation of five state-of-the-art L VLMs (InternVL, Qwen, GOT OCR, LLaMA, MiniCPM) and two traditional OCR systems (Sprinklr-Edge-OCR, SuryaOCR) on a proprietary, doubly hand annotated dataset of multilingual (54 languages) images. Our benchmark covers a broad range of metrics including accuracy, semantic consistency, language coverage, computational efficiency (latency, memory, GPU usage), and deployment cost. T o better reflect real-world applicability, we also conducted edge case deployment analysis, evaluating model performance on CPU only environments. Among the results, Qwen achieved the highest precision (0.54), while Sprinklr-Edge-OCR delivered the best overall F1 score (0.46) and outperformed others in efficiency, processing images 35 faster (0.17 seconds per image on average) and at less than 0.01 of the cost (0.006 Our findings demonstrate that the most optimal OCR systems for edge deployment are the traditional ones even in the era of LLMs due to their low compute requirements, low latency, and very high affordability. Optical Character Recognition (OCR) is a cornerstone technology for digitizing documents, automating data entry, and extracting information from images containing typed, handwritten, or printed text.

Large language models are now routinely used in high-stakes applications where hallucinations can cause serious harm, such as medical consultations or legal advice. Existing hallucination detection methods, however, are impractical for real-world use, as they are either limited to short factual queries or require costly external verification. We present a cheap, scalable method for real-time identification of hallucinated tokens in long-form generations, and scale it effectively to 70B parameter models. Our approach targets \emph{entity-level hallucinations} -- e.g., fabricated names, dates, citations -- rather than claim-level, thereby naturally mapping to token-level labels and enabling streaming detection. We develop an annotation methodology that leverages web search to annotate model responses with grounded labels indicating which tokens correspond to fabricated entities. This dataset enables us to train effective hallucination classifiers with simple and efficient methods such as linear probes. Evaluating across four model families, our classifiers consistently outperform baselines on long-form responses, including more expensive methods such as semantic entropy (e.g., AUC 0.90 vs 0.71 for Llama-3.3-70B), and are also an improvement in short-form question-answering settings. Moreover, despite being trained only with entity-level labels, our probes effectively detect incorrect answers in mathematical reasoning tasks, indicating generalization beyond entities. While our annotation methodology is expensive, we find that annotated responses from one model can be used to train effective classifiers on other models; accordingly, we publicly release our datasets to facilitate reuse. Overall, our work suggests a promising new approach for scalable, real-world hallucination detection.