Large Language Models (LLMs) have emerged as powerful tools for generating coherent text, understanding context, and performing reasoning tasks.However, they struggle with temporal reasoning, which requires processing time-related information such as event sequencing, durations, and inter-temporal relationships.These capabilities are critical for applications including question answering, scheduling, and historical analysis.In this paper, we introduce TISER, a novel framework that enhances the temporal reasoning abilities of LLMs through a multi-stage process that combines timeline construction with iterative self-reflection.Our approach leverages test-time scaling to extend the length of reasoning traces, enabling models to capture complex temporal dependencies more effectively.This strategy not only boosts reasoning accuracy but also improves the traceability of the inference process.Experimental results demonstrate state-of-the-art performance across multiple benchmarks, including out-of-distribution test sets, and reveal that TISER enables smaller open-source models to surpass larger closed-weight models on challenging temporal reasoning tasks. 1 * Work done during an internship at Amazon.Now at Microsoft.

Fact verification aims to verify a claim using evidence from a trustworthy knowledge base. To address this challenge, algorithms must produce features for every claim that are both semantically meaningful, and compact enough to find a semantic alignment with the source information. In contrast to previous work, which tackled the alignment problem by learning over annotated corpora of claims and their corresponding labels, we propose SFAVEL ($\underline{S}$elf-supervised $\underline{Fa}$ct $\underline{Ve}$rification via $\underline{L}$anguage Model Distillation), a novel unsupervised pretraining framework that leverages pre-trained language models to distil self-supervised features into high-quality claim-fact alignments without the need for annotations. This is enabled by a novel contrastive loss function that encourages features to attain high-quality claim and evidence alignments whilst preserving the semantic relationships across the corpora. Notably, we present results that achieve a new state-of-the-art on FB15k-237 (+5.3\% Hits@1) and FEVER (+8\% accuracy) with linear evaluation.

MOTIVATION: The fast growth of bioinformatics adds a significant difficulty to assess the contribution, geographical and thematic distribution of the research publications. RESULTS: To help researchers, grant agencies and general public to assess the progress in bioinformatics, we have developed BIOLITMAP, a web-based geolocation system that allows an easy and sensible exploration of the publications by institution, year and topic. AVAILABILITY AND IMPLEMENTATION: BIOLITMAP is available at http://socialanalytics.bsc.es/biolitmap and the sources have been deposited at https://github.com/inab/BIOLITMAP. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.