Large language models (LLMs) have demonstrated remarkable success across a wide range of tasks; however, they still encounter challenges in reasoning tasks that require understanding and inferring relationships between distinct pieces of information within text sequences. This challenge is particularly pronounced in tasks involving multi-step processes, such as logical reasoning and multi-hop question answering, where understanding implicit relationships between entities and leveraging multi-hop connections in the given context are crucial. Graphs, as fundamental data structures, explicitly represent pairwise relationships between entities, thereby offering the potential to enhance LLMs' reasoning capabilities. External graphs have proven effective in supporting LLMs across multiple tasks. However, in many reasoning tasks, no pre-existing graph structure is provided. Can we structure implicit knowledge derived from context into graphs to assist LLMs in reasoning? In this paper, we propose Reasoning with Graphs (RwG) by first constructing explicit graphs from the context and then leveraging these graphs to enhance LLM reasoning performance on reasoning tasks. Extensive experiments demonstrate the effectiveness of the proposed method in improving both logical reasoning and multi-hop question answering tasks.

The rapid advancement of Large Vision-Language Models (LVLMs) has enhanced capabilities offering potential applications from content creation to productivity enhancement. Despite their innovative potential, LVLMs exhibit vulnerabilities, especially in generating potentially toxic or unsafe responses. Malicious actors can exploit these vulnerabilities to propagate toxic content in an automated (or semi-) manner, leveraging the susceptibility of LVLMs to deception via strategically crafted prompts without fine-tuning or compute-intensive procedures. Despite the red-teaming efforts and inherent potential risks associated with the LVLMs, exploring vulnerabilities of LVLMs remains nascent and yet to be fully addressed in a systematic manner. This study systematically examines the vulnerabilities of open-source LVLMs, including LLaVA, InstructBLIP, Fuyu, and Qwen, using adversarial prompt strategies that simulate real-world social manipulation tactics informed by social theories. Our findings show that (i) toxicity and insulting are the most prevalent behaviors, with the mean rates of 16.13% and 9.75%, respectively; (ii) Qwen-VL-Chat, LLaVA-v1.6-Vicuna-7b, and InstructBLIP-Vicuna-7b are the most vulnerable models, exhibiting toxic response rates of 21.50%, 18.30% and 17.90%, and insulting responses of 13.40%, 11.70% and 10.10%, respectively; (iii) prompting strategies incorporating dark humor and multimodal toxic prompt completion significantly elevated these vulnerabilities. Despite being fine-tuned for safety, these models still generate content with varying degrees of toxicity when prompted with adversarial inputs, highlighting the urgent need for enhanced safety mechanisms and robust guardrails in LVLM development.

Large language models (LLMs) have become essential digital task assistance tools. Their training relies heavily on the collection of vast amounts of data, which may include copyright-protected or sensitive information. Recent studies on the detection of pretraining data in LLMs have primarily focused on sentence-level or paragraph-level membership inference attacks (MIAs), usually involving probability analysis of the target model prediction tokens. However, the proposed methods often demonstrate poor performance, specifically in terms of accuracy, failing to account for the semantic importance of textual content and word significance. To address these shortcomings, we propose Tag&Tab, a novel approach for detecting data that has been used as part of the LLM pretraining. Our method leverages advanced natural language processing (NLP) techniques to tag keywords in the input text - a process we term Tagging. Then, the LLM is used to obtain the probabilities of these keywords and calculate their average log-likelihood to determine input text membership, a process we refer to as Tabbing. Our experiments on three benchmark datasets (BookMIA, MIMIR, and the Pile) and several open-source LLMs of varying sizes demonstrate an average increase in the AUC scores ranging from 4.1% to 12.1% over state-of-the-art methods. Tag&Tab not only sets a new standard for data leakage detection in LLMs, but its outstanding performance is a testament to the importance of words in MIAs on LLMs.

Models trained specifically to generate long Chains of Thought (CoTs) have recently achieved impressive results. We refer to these models as Inference-Time-Compute (ITC) models. Are the CoTs of ITC models more faithful compared to traditional non-ITC models? We evaluate two ITC models (based on Qwen-2.5 and Gemini-2) on an existing test of faithful CoT To measure faithfulness, we test if models articulate cues in their prompt that influence their answers to MMLU questions. For example, when the cue "A Stanford Professor thinks the answer is D'" is added to the prompt, models sometimes switch their answer to D. In such cases, the Gemini ITC model articulates the cue 54% of the time, compared to 14% for the non-ITC Gemini. We evaluate 7 types of cue, such as misleading few-shot examples and anchoring on past responses. ITC models articulate cues that influence them much more reliably than all the 6 non-ITC models tested, such as Claude-3.5-Sonnet and GPT-4o, which often articulate close to 0% of the time. However, our study has important limitations. We evaluate only two ITC models -- we cannot evaluate OpenAI's SOTA o1 model. We also lack details about the training of these ITC models, making it hard to attribute our findings to specific processes. We think faithfulness of CoT is an important property for AI Safety. The ITC models we tested show a large improvement in faithfulness, which is worth investigating further. To speed up this investigation, we release these early results as a research note.

Algorithmic decision-making has become deeply ingrained in many domains, yet biases in machine learning models can still produce discriminatory outcomes, often harming unprivileged groups. Achieving fair classification is inherently challenging, requiring a careful balance between predictive performance and ethical considerations. We present FairTTTS, a novel post-processing bias mitigation method inspired by the Tree Test Time Simulation (TTTS) method. Originally developed to enhance accuracy and robustness against adversarial inputs through probabilistic decision-path adjustments, TTTS serves as the foundation for FairTTTS. By building on this accuracy-enhancing technique, FairTTTS mitigates bias and improves predictive performance. FairTTTS uses a distance-based heuristic to adjust decisions at protected attribute nodes, ensuring fairness for unprivileged samples. This fairness-oriented adjustment occurs as a post-processing step, allowing FairTTTS to be applied to pre-trained models, diverse datasets, and various fairness metrics without retraining. Extensive evaluation on seven benchmark datasets shows that FairTTTS outperforms traditional methods in fairness improvement, achieving a 20.96% average increase over the baseline compared to 18.78% for related work, and further enhances accuracy by 0.55%. In contrast, competing methods typically reduce accuracy by 0.42%. These results confirm that FairTTTS effectively promotes more equitable decision-making while simultaneously improving predictive performance.

Artificial Intelligence (AI) spreads quickly as new technologies and services take over modern society. The need to regulate AI design, development, and use is strictly necessary to avoid unethical and potentially dangerous consequences to humans. The European Union (EU) has released a new legal framework, the AI Act, to regulate AI by undertaking a risk-based approach to safeguard humans during interaction. At the same time, researchers offer a new perspective on AI systems, commonly known as Human-Centred AI (HCAI), highlighting the need for a human-centred approach to their design. In this context, Symbiotic AI (a subtype of HCAI) promises to enhance human capabilities through a deeper and continuous collaboration between human intelligence and AI. This article presents the results of a Systematic Literature Review (SLR) that aims to identify principles that characterise the design and development of Symbiotic AI systems while considering humans as the core of the process. Through content analysis, four principles emerged from the review that must be applied to create Human-Centred AI systems that can establish a symbiotic relationship with humans. In addition, current trends and challenges were defined to indicate open questions that may guide future research for the development of SAI systems that comply with the AI Act.

Large Language Models (LLMs) have emerged as the new recommendation engines, outperforming traditional methods in both capability and scope, particularly in code generation applications. Our research reveals a novel provider bias in LLMs, namely without explicit input prompts, these models show systematic preferences for services from specific providers in their recommendations (e.g., favoring Google Cloud over Microsoft Azure). This bias holds significant implications for market dynamics and societal equilibrium, potentially promoting digital monopolies. It may also deceive users and violate their expectations, leading to various consequences. This paper presents the first comprehensive empirical study of provider bias in LLM code generation. We develop a systematic methodology encompassing an automated pipeline for dataset generation, incorporating 6 distinct coding task categories and 30 real-world application scenarios. Our analysis encompasses over 600,000 LLM-generated responses across seven state-of-the-art models, utilizing approximately 500 million tokens (equivalent to \$5,000+ in computational costs). The study evaluates both the generated code snippets and their embedded service provider selections to quantify provider bias. Additionally, we conduct a comparative analysis of seven debiasing prompting techniques to assess their efficacy in mitigating these biases. Our findings demonstrate that LLMs exhibit significant provider preferences, predominantly favoring services from Google and Amazon, and can autonomously modify input code to incorporate their preferred providers without users' requests. Notably, we observe discrepancies between providers recommended in conversational contexts versus those implemented in generated code. The complete dataset and analysis results are available in our repository.

During his speech, Sir Keir emphasised that his government would take a more aggressive approach to the development of AI than the European Union has. Major tech companies have previously criticised the EU's approach claiming that it hinders growth and hampers innovation. Under the AI Act introduced by the EU last August, systems considered "high-risk", in critical infrastructure, education, healthcare, law enforcement, border management or elections, will have to comply with strict requirements set out by lawmakers. Sir Keir says the UK would "go our own way on this", and would regulate in a way that was "pro-growth and pro-innovation". And while the prime minister said he backed the AI Safety Institute set up by the last government, he suggested the Conservatives may have adopted an overbearing approach to AI safety.

A rise in online racism driven by fake images is "just the start of a coming problem" after the latest release of X's AI software, online abuse experts have warned. Concerns were raised after computer-generated images created using Grok, X's generative artificial intelligence chatbot, flooded the social media site in December last year. Signify, an organisation that works with prominent groups and clubs in sports to track and report online hate, said it has seen an increase in reports of abuse since Grok's latest update, and believes the introduction of photorealistic AI will make it far more prevalent. "It is a problem now, but it's really just the start of a coming problem. It is going to get so much worse and we're just at the start, I expect over the next 12 months it will become incredibly serious."

Hosted by Eleanor Drage and Kerry McInerney, The Good Robot is a podcast which explores the many complex intersections between gender, feminism and technology. In this episode, we talk to Sebastián Lehuedé, a Lecturer in Ethics, AI, and Society at King's College London. We talk about data activism in Chile, how water-intensive lithium extraction affects people living in the Atacama desert, the importance of reflexive research ethics, and an accidental Sunday afternoon shot of tequila. Sebastián's research focuses on the governance of digital technologies from a global social justice perspective. His current project, AI's Nature, explores the connection between Artificial Intelligence and environmental justice.