Natural Language Processing

Researchers developed AWARE-FX, an auditable AI/NLP system that converts corporate annual report text into traceable firm-year hedging-disclosure measures, and tested it on 24,909 Hong Kong firm-years from 2008 to 2025, …

Researchers present B1ade, an efficient retrieval-augmented generation (RAG) architecture with a 335M parameter embedding model and a 1B parameter small language model (SLM). B1ade-embed achieves top MTEB scores among su…

Researchers introduced MiGUE-Bench, a benchmark for evaluating large language models (LLMs) on multi-granularity event analysis, covering tasks from event detection to future prediction. The benchmark uses an LLM-driven …

A new arXiv preprint (2607.27566v1) finds that direct answer-only supervised fine-tuning (SFT) on MedGemma-1.5-4B is the most robust adaptation method for multi-frame medical visual question answering on the MedFrameQA b…

Researchers introduced OVEarth-Bench, a benchmark for open-vocabulary Earth observation that expands category breadth and query diversity, finding that current methods perform limitedly, with MLLM-based methods achieving…

Researchers propose SentiLLM, a framework that uses Semantic-Aligned Structural Abstraction to improve multimodal sentiment analysis by converting non-verbal signals into text-like tokens for large language models. The m…

Researchers propose Conditional Retrieval Alignment (CoRA), a gradient-free framework that converts a frozen encoder into a task-conditioned retriever for on-device in-context learning, using closed-form ridge regression…

A developer built EasyStock, an AI assistant that converts natural-language queries into stock screening criteria, fetching market data and providing explainable results. The tool aims to simplify stock screening by allo…

Betocmn released Widen, an open-source (MIT) native Mac app built with Swift that serves as a Postgres GUI with text-to-SQL capabilities, supporting local or cloud LLMs via OpenRouter or Apple's on-device model. The app,…

ElevenLabs has introduced Expressive Mode, a feature within its ElevenLabs Agents platform that adds emotional tone and inflection control to real-time voice agents, allowing them to sound annoyed, amused, sarcastic, or …

Rui Sousa-Silva, in a paper presented at the Second International Conference on Natural Language Processing and Artificial Intelligence for Cyber Security (NLPAICS) in Alicante, Spain, in June 2026, found that forensic l…

Researchers Bruno Franco and Edson Scalabrin introduced Compositional Graph Similarity (CGS), a graph-based metric for evaluating Transformer models on the ReCOGS benchmark, and found that the lowest-scoring categories a…

Researchers Ivan Martinez-Murillo, Robiert Sepúlveda-Torres, and Juan Pablo Consuegra-Ayala found that transformer-based fraud detection models trained only on English achieve near-perfect in-language performance (F1 ≈ 0…

Researchers Chit-Fung Lam and Elaine Uí Dhonnchadha presented the development of Cantonese and Irish treebanks within the Parallel Grammar (ParGram) Project at the Third Workshop on the Bridges and Gaps between Formal an…

A study by Yan Cong and Julia Rayz, presented at the Third Workshop on the Bridges and Gaps between Formal and Computational Linguistics (BriGap-3) in Paris, France, in July 2026, found that current vision-language model…

Koharu Saeki and Daisuke Bekki from Ochanomizu University introduced Express, a web-based interactive development environment for the Japanese automated inference system lightblue, which shifts grammar development from e…

Researchers Artem Saloev, Erin Pacquetet, and Nicolas Ballier found that the ABX experiment with Mimi's semantic token codebook fails to capture the mapping of semantic tokens to phone realisations, but by realigning Mim…

Priscilla Adenuga's paper, presented at the Second International Conference on Natural Language Processing and Artificial Intelligence for Cyber Security (NLPAICS) in June 2026 in Alicante, Spain, argues that prompt inje…

Researchers Nanako Miyagawa, Hinari Daido, and Daisuke Bekki introduced Neural Wani, an integration of a lightweight LSTM-based neural model into the automated theorem prover wani for Dependent Type Theory, achieving a 1…

Judith Sieker and Sina Zarrieß, in a position paper presented at the Third Workshop on the Bridges and Gaps between Formal and Computational Linguistics (BriGap-3) in Paris, France, in July 2026, argue that misalignments…