The structure of naming systems in natural languages hinges on a trade-off between high informativeness and low complexity. Prior work capitalizes on information theory to formalize these notions; however, these studies generally rely on two simplifications: (i) optimal listeners, and (ii) universal communicative need across languages. Here, we address these limitations by introducing an information-theoretic framework for discrete object naming systems, and we use it to prove that an optimal trade-off is achievable if and only if the listener's decoder is equivalent to the Bayesian decoder of the speaker. Adopting a referential game setup from emergent communication, and focusing on the semantic domain of kinship, we show that our notion of optimality is not only theoretically achievable but also emerges empirically in learned communication systems.

Differentiable inductive logic programming (ILP) techniques have proven effective at finding approximate rule-based solutions to link prediction and node classification problems on knowledge graphs; however, the common assumption of chain-like rule structure can hamper the performance and interpretability of existing approaches. We introduce GLIDR, a differentiable rule learning method that models the inference of logic rules with more expressive syntax than previous methods. GLIDR uses a differentiable message passing inference algorithm that generalizes previous chain-like rule learning methods to allow rules with features like branches and cycles. GLIDR has a simple and expressive rule search space which is parameterized by a limit on the maximum number of free variables that may be included in a rule. Explicit logic rules can be extracted from the weights of a GLIDR model for use with symbolic solvers. We demonstrate that GLIDR can significantly outperform existing rule learning methods on knowledge graph completion tasks and even compete with embedding methods despite the inherent disadvantage of being a structure-only prediction method. We show that rules extracted from GLIDR retain significant predictive performance, and that GLIDR is highly robust to training data noise. Finally, we demonstrate that GLIDR can be chained with deep neural networks and optimized end-to-end for rule learning on arbitrary data modalities.

Recent advancements in Large Language Model (LLM) alignment have sought to mitigate the cost of human annotations by leveraging pretrained models to generate preference data. However, existing methods often compare responses from models with substantially different capabilities, yielding superficial distinctions that fail to provide meaningful guidance on what constitutes a superior response. To address this limitation, we propose Kinship-Aware pReference MApping (KARMA), a novel framework that systematically pairs responses from models with comparable competencies. By constraining preference comparisons to outputs of similar complexity and quality, KARMA enhances the informativeness of preference data and improves the granularity of alignment signals. Empirical evaluations demonstrate that our kinship-aware approach leads to more consistent and interpretable alignment outcomes, ultimately facilitating a more principled and reliable pathway for aligning LLM behavior with human preferences.

Languages are known to describe the world in diverse ways. Across lexicons, diversity is pervasive, appearing through phenomena such as lexical gaps and untranslatability. However, in computational resources, such as multilingual lexical databases, diversity is hardly ever represented. In this paper, we introduce a method to enrich computational lexicons with content relating to linguistic diversity. The method is verified through two large-scale case studies on kinship terminology, a domain known to be diverse across languages and cultures: one case study deals with seven Arabic dialects, while the other one with three Indonesian languages. Our results, made available as browseable and downloadable computational resources, extend prior linguistics research on kinship terminology, and provide insight into the extent of diversity even within linguistically and culturally close communities.

UFO expert Nick Pope discuss the whistleblower claiming that the U.S. has alien crafts and remains on'Fox News @ Night.' A Harvard professor of astronomy is predicting extraterrestrials will make contact with artificial intelligence before humans, due to aliens potentially feeling a "kinship" with human technology. "My expectation from interstellar travel is that it's best done with electronic gadgets and devices rather than with biological creatures because the journey takes a long time," Harvard professor Avi Loeb said in an upcoming documentary titled "God Vs. "Even to the nearest star, it will take us 50,000 years to get there with chemical rockets. And artificial intelligence systems have that patience - and then they can remain dormant ... so that they survive the journey," he said. Space agencies across the world, including NASA and the European Space Agency, have for years been using AI technology to chart galaxies and stars and even send robots to other planets. Avi Loeb, Frank B. Baird Jr. Professor of Science at Harvard University, speaks during the SALT conference in Manhattan, New York City, U.S., September 14, 2022. Loeb said extraterrestrials would likely reach out to artificial intelligence before humans due to a likely "kinship." "If they visit us, of course, we can use our AI systems to interpret their AI systems.

Pre-trained large language models (LMs) struggle to perform logical reasoning reliably despite advances in scale and compositionality. In this work, we tackle this challenge through the lens of symbolic programming. We propose DSR-LM, a Differentiable Symbolic Reasoning framework where pre-trained LMs govern the perception of factual knowledge, and a symbolic module performs deductive reasoning. In contrast to works that rely on hand-crafted logic rules, our differentiable symbolic reasoning framework efficiently learns weighted rules and applies semantic loss to further improve LMs. DSR-LM is scalable, interpretable, and allows easy integration of prior knowledge, thereby supporting extensive symbolic programming to robustly derive a logical conclusion. The results of our experiments suggest that DSR-LM improves the logical reasoning abilities of pre-trained language models, resulting in a significant increase in accuracy of over 20% on deductive reasoning benchmarks. Furthermore, DSR-LM outperforms a variety of competitive baselines when faced with systematic changes in sequence length.

The world around us is vibrating with sounds we cannot hear. Bats chitter and babble in ultrasound; elephants rumble infrasonic secrets to each other; coral reefs are aquatic clubs, hopping with the cracks and hisses and clicks of marine life. For centuries, we didn't even know those sounds existed. But as technology has advanced, so has our capacity to listen. Today, tools like drones, digital recorders, and artificial intelligence are helping us listen to the sounds of nature in unprecedented ways, transforming the world of scientific research and raising a tantalizing prospect: Someday soon, computers might allow us to talk to animals. In some ways, that has already begun.

We are about 25 years from an AI asking us why we think we have the right to own them. What are we going to say to them? We've had plenty of time to prepare. Science fiction writers have been considering the idea since Isaac Asimov wrote the Bicentennial Man, and probably well before. Star Trek has explored it head-on on at least two occasions, and the entire character arcs of both Data and The Doctor revolve around this question.

Multi-hop reasoning is an effective approach for query answering (QA) over incomplete knowledge graphs (KGs). The problem can be formulated in a reinforcement learning (RL) setup, where a policy-based agent sequentially extends its inference path until it reaches a target. However, in an incomplete KG environment, the agent receives low-quality rewards corrupted by false negatives in the training data, which harms generalization at test time. Furthermore, since no golden action sequence is used for training, the agent can be misled by spurious search trajectories that incidentally lead to the correct answer. We propose two modeling advances to address both issues: (1) we reduce the impact of false negative supervision by adopting a pretrained one-hop embedding model to estimate the reward of unobserved facts; (2) we counter the sensitivity to spurious paths of on-policy RL by forcing the agent to explore a diverse set of paths using randomly generated edge masks. Our approach significantly improves over existing path-based KGQA models on several benchmark datasets and is comparable or better than embedding-based models.