IJCCI 2025 (17th International Joint Conference on Computational Intelligence) received 146 paper submissions from 41 countries. To evaluate each submission, a double-blind paper review was performed by the Program Committee. After a stringent selection process, 36 papers were published and presented as full papers, i.e. completed work (12 pages/25' oral presentation), 83 papers were accepted as short papers (58 as oral presentation). The organizing committee included the IJCCI Conference Chair: Joaquim Filipe, Polytechnic Institute of Setubal, Portugal, and the IJCCI 2025 Program Chairs: Francesco Marcelloni, University of Pisa, Italy, Kurosh Madani, University of Paris-EST Créteil (UPEC), France, and Niki van Stein, Leiden University, Netherlands. At the closing session, the conference acknowledged a few papers that were considered excellent in their class, presenting a "Best Paper Award", "Best Student Paper Award", and "Best Poster Award" for each of the co-located conferences.

Animal trials helped to restore order when the unspeakable happened. In 1457, a sow and her piglets were put on trial for the murder of a child in the village of Savigny in Burgundy, France. The sow was ultimately found guilty and her piglets were acquitted. Breakthroughs, discoveries, and DIY tips sent six days a week. It's a common scene in many films set in medieval Europe: a wooden cart wheeling its way through a jeering crowd of townsfolk, taking a condemned prisoner to the gallows.

This paper presents a formal, categorical framework for analysing how humans and large language models (LLMs) transform content into truth-evaluated propositions about a state space of possible worlds W , in order to argue that LLMs do not solve but circumvent the symbol grounding problem.

Large language models (LLMs) possess vast knowledge acquired from extensive training corpora, but they often cannot remove specific pieces of information when needed, which makes it hard to handle privacy, bias mitigation, and knowledge correction. Traditional model unlearning approaches require computationally expensive fine-tuning or direct weight editing, making them impractical for real-world deployment. In this work, we introduce LoRA-based Unlearning with Negative Examples (LUNE), a lightweight framework that performs negative-only unlearning by updating only low-rank adapters while freezing the backbone, thereby localizing edits and avoiding disruptive global changes. Leveraging Low-Rank Adaptation (LoRA), LUNE targets intermediate representations to suppress (or replace) requested knowledge with an order-of-magnitude lower compute and memory than full fine-tuning or direct weight editing. Extensive experiments on multiple factual unlearning tasks show that LUNE: (I) achieves effectiveness comparable to full fine-tuning and memory-editing methods, and (II) reduces computational cost by about an order of magnitude.

The town was important to the Celtic Mediomatrici tribe before it was conquered by Julius Caesar. Breakthroughs, discoveries, and DIY tips sent every weekday. Archeologists recently discovered over 40,000 Roman-era coins during a dig in a French village. The treasure trove of ancient coins were found in three ceramic storage vessels that had been buried between 1,700 and 1,800 years ago. The team from the National Institute for Preventive Archaeological Research (INRAP) was digging in the village of Senon in northeastern France, roughly 60 miles from the Luxembourg border.

This paper systematically examines nation-level biases exhibited by Large Language Models (LLMs) within the domain of International Relations (IR). Leveraging historical records from the United Nations Security Council (UNSC), we developed a bias evaluation framework comprising three distinct tests to explore nation-level bias in various LLMs, with a particular focus on the five permanent members of the UNSC. Experimental results show that, even with the general bias patterns across models (e.g., favorable biases toward the western nations, and unfavorable biases toward Russia), these still vary based on the LLM. Notably, even within the same LLM, the direction and magnitude of bias for a nation change depending on the evaluation context. This observation suggests that LLM biases are fundamentally multidimensional, varying across models and tasks. We also observe that models with stronger reasoning abilities show reduced bias and better performance. Building on this finding, we introduce a debiasing framework that improves LLMs' factual reasoning combining Retrieval-Augmented Generation with Reflexion-based self-reflection techniques. Experiments show it effectively reduces nation-level bias, and improves performance, particularly in GPT-4o-mini and LLama-3.3-70B. Our findings emphasize the need to assess nation-level bias alongside performance when applying LLMs in the IR domain.

Thousands of Airbus planes are being returned to normal service after being grounded for hours due to a warning that solar radiation could interfere with onboard flight control computers. The aerospace giant - based in France - said around 6,000 of its A320 planes had been affected with most requiring a quick software update. Some 900 older planes need a replacement computer. French Transport Minister Philippe Tabarot said the updates went very smoothly for more than 5,000 planes. Fewer than 100 aircraft still needed the update, Airbus had told him, according to local media.

Is the fall of Pokrovsk inevitable? Is Trump losing patience with Putin? A Russian missile strike on the eastern Ukrainian city of Balakliia killed three people and wounded 10, including three children, a regional military official in the Kharkiv region said on Telegram on Monday. At least two people were killed and three were injured in Russian shelling of the Nikopol district in Ukraine's Dnipropetrovsk region, Vladyslav Haivanenko, the acting head of the Dnipropetrovsk Regional Military Administration, wrote on Facebook. Russian troops captured three villages across three Ukrainian regions, the RIA news agency cited the Russian Ministry of Defence as saying on Monday.

Can Israel annex the West Bank if the US says no? Will the US plan for Gaza fail? 'We survived the war, we may not survive the ceasefire' Who are the 95 healthcare workers held by Israel? The United Nations and France have condemned an Israeli attack that hit UN peacekeeping troops in southern Lebanon. UN spokesperson Stephane Dujarric said on Monday that the previous day's attack on UNIFIL troops, which he said involved an Israeli drone dropping a grenade in the vicinity of a patrol, as well as a tank opening fire on peacekeepers near the border town of Kfar Kila, was "very, very dangerous". Israel has violated the truce on a near-daily basis.