Researchers at the Seventh Workshop on Natural Language Processing and Computational Social Science found that emojis, while rarely offensive alone, can acquire harmful meanings through symbolic assoc…
Even frontier large language models such as GPT-5.2 and leading open-weight alternatives consistently underperform fine-tuned BERT on a challenging legal reasoning task, according to a study by Caroli…
A study by Joseph James presented at the Seventh Workshop on Natural Language Processing and Computational Social Science in July 2026 found that 16 Japanese-capable large language models showed subst…
Researchers Alexandria Leto and Maria Leonor Pacheco introduced an unsupervised LLM-based method for conceptual metaphor discovery in political discourse, demonstrating its utility through a case stud…
Researchers at the University of Maryland found that the community size of early adopters and emoji semantics are positively correlated with the popularity of newly released emojis on Twitter. Analyzi…
Researchers Duy Dang Phu and Thìn Đặng Văn have developed an NLP framework combining relevance filtering, topic modeling, and LLM-assisted interpretation to analyze corporate strategic behavior in the…
USC Viterbi and USC Stevens researchers will present papers at ACL 2025 on using AI for suicide prevention and generating long-horizon web tasks. One study analyzed 270,000 suicide records with AI to …
Kakao Bank's Financial Tech Lab had four papers on financial AI safety accepted at major AI conferences in 2026, including research on detecting prompt injection attacks and an AI safety evaluation fr…
Researchers presented AURA-ST, a three-stage modular pipeline for low-resource speech-to-text translation at IWSLT 2026. The system bypasses traditional cross-attention by treating projected acoustic …
Researchers from an undisclosed institution introduced AlignAtt4LLM, the first application of the AlignAtt policy to decoder-only large language models for simultaneous speech translation at IWSLT 202…
Researchers from KIT submitted a cross-lingual voice cloning system to the IWSLT 2026 track, building on FishAudio-S2-Pro with language tag prompting, reinforcement learning fine-tuning, and reference…
Researchers evaluated four state-of-the-art zero-shot cross-lingual voice cloning systems across six languages, finding that Arabic remains particularly challenging. The study, presented at IWSLT 2026…
Researchers introduced Patent-CR, the first English dataset for patent claim revision, containing rejected and granted patent claims. Evaluating large language models, they found GPT-4 performed best …
Researchers at the 2025 Conference on Empirical Methods in Natural Language Processing introduced PatentScore, a multi-dimensional evaluation framework for LLM-generated patent claims. PatentScore int…
Researchers introduced DySECT, a dynamic self-evolving extraction system that uses a closed-loop cycle where an LLM extracts triples to populate a knowledge base, which then improves the LLM via promp…
Researchers from multiple institutions published a comprehensive survey on Process Reward Models (PRMs) at ACL 2026, covering data generation, model construction, and usage for step-level reasoning ev…
Researchers introduced TRuST, a large-scale dataset with ~300k annotations for toxicity recognition, unifying prior resources through a synthesized definition. Benchmarking showed fine-tuned PLMs outp…
Researchers at ACL 2026 introduced a method to reuse LLM hidden states for classification tasks, training lightweight probes on token- and layer-selective representations to eliminate separate guard m…
Researchers at the 64th Annual Meeting of the Association for Computational Linguistics introduced a dual-task paradigm combining arithmetic and sentence comprehension to study how language models all…
Researchers Bhavik Chandna and Procheta Sen introduced a counterfactual explanation framework for retrieval models that identifies which terms need to be added to a document to improve its ranking, ad…