Researchers from Singapore developed a Signed Belief Graph Neural Network (SiBeGNN) for topic modeling in conspiratorial discourse, achieving a cDBI of 8.38 versus 13.60–67.27 for standard methods. Th…
A study by researchers at the University of Vermont found that large language models (LLMs) exhibit systematic gender bias when detecting intimate partner violence (IPV), with abuse and intent detecti…
A study by Maximilian Weber and Johannes B. Gruber analyzing Twitter data found that Meta's Galactica, marketed as a scientific assistant, faced rapidly escalating negative sentiment after its Novembe…
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 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…
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…
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…
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 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…
Barcelona Supercomputing Center submitted an end-to-end system combining a speech encoder with a translation-oriented large language model to the instruction following track of IWSLT 2026. The system …
Researchers from the Karlsruhe Institute of Technology developed Diet-KIT, a post-training quantization system that compresses the Qwen2-Audio-7B speech LLM from 16 GB to 3.98 GB while maintaining tra…
HW-TSC submitted a cascaded system to the IWSLT 2026 Subtitling track, using a large-model-based streaming speech recognition framework with VAD, sliding-window context caching, long audio chunking, a…
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…
The CUHKSZ team submitted a simultaneous speech translation system to IWSLT 2026, built on Qwen3-Omni-30B-A3B with LoRA adaptation, achieving 40.5 BLEU for English→Chinese and 27.7 BLEU for English→Ge…
Researchers from IIIT-BGP presented low-resource Bhojpuri-Hindi speech translation systems at IWSLT 2026, including an end-to-end model combining Wav2Vec2 and NLLB-200 with a lightweight adapter, and …
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 at Ohio State University developed HydraQE, an end-to-end, reference-free quality estimation system for speech translation that outperforms cascaded text-based baselines. Submitted to the …
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 TRuST, a large-scale dataset with ~300k annotations for toxicity recognition, unifying prior resources through a synthesized definition. Benchmarking showed fine-tuned PLMs outp…