Large language models (LLMs) are a promising venue for natural language understanding and generation. However, current LLMs are far from reliable: they are prone to generating non-factual information and, more crucially, to contradicting themselves when prompted to reason about relations between entities of the world. These problems are currently addressed with large scale fine-tuning or by delegating reasoning to external tools. In this work, we strive for a middle ground and introduce a loss based on neuro-symbolic reasoning that teaches an LLM to be logically consistent with an external set of facts and rules and improves self-consistency even when the LLM is fine-tuned on a limited set of facts. Our approach also allows to easily combine multiple logical constraints at once in a principled way, delivering LLMs that are more consistent w.r.t. all constraints and improve over several baselines w.r.t. a given constraint. Moreover, our method allows LLMs to extrapolate to unseen but semantically similar factual knowledge, represented in unseen datasets, more systematically.

A new report found the British Broadcasting Corporation (BBC) guilty of violating its own editorial guidelines over a thousand times in its coverage of the Israel-Hamas war. According to The Telegraph, the report analyzed four months of BBC output on television, radio, online, podcasts and on social media during the height of the conflict and found a "deeply worrying pattern of bias" against Israel. British lawyer Trevor Asserson and a team of about 20 lawyers and 20 data scientists used artificial intelligence to analyze nine million words from the news outlet, starting the day of the October 7, 2023, terror attack. The researchers allegedly identified 1,553 instances where the BBC violated its own editorial guidelines on impartiality, accuracy, editorial values and public interest. Hundreds attend a protest called by the National Jewish Assembly, The Campaign Against Antisemitsim and the UK Lawyers for Israel at the BBC Broadcasting House on October 16, 2023, in London, England.

The Houthis have claimed to have shot down a United States military drone over Yemen, in the latest attack by the group, which has disrupted shipping trade through the crucial Bab al-Mandeb Strait, drawing US strikes. The Yemeni group has carried out dozens of attacks on ships with links to Israel in a show of solidarity with Palestinians amid Israel's 11-month-old war on Gaza. Yahya Saree, the military spokesman of the Houthi group, said in a prerecorded video message released early on Sunday that the MQ-9 Reaper was shot down by air defences over Marib as "it was carrying out hostile activities". This is the eighth drone of this type to be shot down since the start of the war on Gaza, he said. The group has not so far released footage of the downed attack and surveillance aircraft that costs about 30m.

Large Language Models (LLMs) have rapidly increased in size and apparent capabilities in the last three years, but their training data is largely English text. There is growing interest in multilingual LLMs, and various efforts are striving for models to accommodate languages of communities outside of the Global North, which include many languages that have been historically underrepresented in digital realms. These languages have been coined as "low resource languages" or "long-tail languages", and LLMs performance on these languages is generally poor. While expanding the use of LLMs to more languages may bring many potential benefits, such as assisting cross-community communication and language preservation, great care must be taken to ensure that data collection on these languages is not extractive and that it does not reproduce exploitative practices of the past. Collecting data from languages spoken by previously colonized people, indigenous people, and non-Western languages raises many complex sociopolitical and ethical questions, e.g., around consent, cultural safety, and data sovereignty. Furthermore, linguistic complexity and cultural nuances are often lost in LLMs. This position paper builds on recent scholarship, and our own work, and outlines several relevant social, cultural, and ethical considerations and potential ways to mitigate them through qualitative research, community partnerships, and participatory design approaches. We provide twelve recommendations for consideration when collecting language data on underrepresented language communities outside of the Global North.

Language model alignment research often attempts to ensure that models are not only helpful and harmless, but also truthful and unbiased. However, optimizing these objectives simultaneously can obscure how improving one aspect might impact the others. In this work, we focus on analyzing the relationship between two concepts essential in both language model alignment and political science: \textit{truthfulness} and \textit{political bias}. We train reward models on various popular truthfulness datasets and subsequently evaluate their political bias. Our findings reveal that optimizing reward models for truthfulness on these datasets tends to result in a left-leaning political bias. We also find that existing open-source reward models (i.e. those trained on standard human preference datasets) already show a similar bias and that the bias is larger for larger models. These results raise important questions about both the datasets used to represent truthfulness and what language models capture about the relationship between truth and politics.

Large language models (LLMs) have achieved impressive performance on code generation. Although prior studies enhanced LLMs with prompting techniques and code refinement, they still struggle with complex programming problems due to rigid solution plans. In this paper, we draw on pair programming practices to propose PairCoder, a novel LLM-based framework for code generation. PairCoder incorporates two collaborative LLM agents, namely a Navigator agent for high-level planning and a Driver agent for specific implementation. The Navigator is responsible for proposing promising solution plans, selecting the current optimal plan, and directing the next iteration round based on execution feedback. The Driver follows the guidance of Navigator to undertake initial code generation, code testing, and refinement. This interleaved and iterative workflow involves multi-plan exploration and feedback-based refinement, which mimics the collaboration of pair programmers. We evaluate PairCoder with both open-source and closed-source LLMs on various code generation benchmarks. Extensive experimental results demonstrate the superior accuracy of PairCoder, achieving relative pass@1 improvements of 12.00%-162.43% compared to prompting LLMs directly.

In today's era, Neural Networks (NN) are applied in various scientific fields such as robotics, medicine, engineering, etc. However, the predictions of neural networks themselves contain a degree of uncertainty that must always be taken into account before any decision is made. This is why many researchers have focused on developing different ways to quantify the uncertainty of neural network predictions. Some of these methods are based on generating prediction intervals (PI) via neural networks for the requested target values. The SEF (Shifting the Error Function) method presented in this paper is a new method that belongs to this category of methods. The proposed approach involves training a single neural network three times, thus generating an estimate along with the corresponding upper and lower bounds for a given problem. A pivotal aspect of the method is the calculation of a parameter from the initial network's estimates, which is then integrated into the loss functions of the other two networks. This innovative process effectively produces PIs, resulting in a robust and efficient technique for uncertainty quantification. To evaluate the effectiveness of our method, a comparison in terms of successful PI generation between the SEF, PI3NN and PIVEN methods was made using two synthetic datasets.

This paper introduces a novel approach to interactive robots by leveraging the form-factor of cards to create thin robots equipped with vibrational capabilities for locomotion and haptic feedback. The system is composed of flat-shaped robots with on-device sensing and wireless control, which offer lightweight portability and scalability. This research introduces a hardware prototype. Applications include augmented card playing, educational tools, and assistive technology, which showcase CARDinality's versatility in tangible interaction.

The influence of individual differences on the perception and evaluation of interactions with robots has been researched for decades. Some human demographic characteristics have been shown to affect how individuals perceive interactions with robots. Still, it is to-date not clear whether, which and to what extent individual differences influence how we perceive robots, and even less is known about human factors and their effect on the perception of robot movements. In addition, most results on the relevance of individual differences investigate human-robot interactions with humanoid or social robots whereas interactions with industrial robots are underrepresented. We present a literature review on the relationship of robot movements and the influence of demographic variation. Our review reveals a limited comparability of existing findings due to a lack of standardized robot manipulations, various dependent variables used and differing experimental setups including different robot types. In addition, most studies have insufficient sample sizes to derive generalizable results. To overcome these shortcomings, we report the results from a Web-based experiment with 930 participants that studies the effect of demographic characteristics on the evaluation of movement behaviors of an articulated robot arm. Our findings demonstrate that most participants prefer an approach from the side, a large movement range, conventional numbers of rotations, smooth movements and neither fast nor slow movement speeds. Regarding individual differences, most of these preferences are robust to demographic variation, and only gender and age was found to cause slight preference differences between slow and fast movements.

Narrative systems, such as dialogue and storytelling systems, often utilize persona profiles to enhance personalized interactions. Existing persona profiles frequently exhibit biases, posing risks to system integrity and fairness. To address this, we introduce the UPCS framework, which categorizes character descriptions into eight dimensions, including bias mitigation strategies. Experimental results demonstrate UPCS's superiority in accuracy, diversity, bias elimination, and user satisfaction, marking a significant advancement in persona construction for reliable narrative systems.