Lost in Speech: Trilingual Spoken Hallucination Detection Across Audio and Transcripts
Trilingual spoken hallucination detection, comparing what is detectable from raw audio against what survives transcription.
meruyert-aristombayeva
•
•
1 min read
AOR-Bench: Do Large Audio Language Models Over-Refuse Pseudo-Harmful Queries?
A benchmark for over-refusal in large audio language models — how often they decline pseudo-harmful but benign spoken queries, and what drives it.
jiaxi-yang
Position: Breaking the Dual Curse of Multilingual AI Requires Socio-Technical Guardrails, Not Post-Hoc Alignment
A position paper arguing that the dual curse of multilingual AI — 35% harmful generation and near-random reward-model accuracy in low-resource languages — cannot be fixed by …
DIA-HARM: Dialectal Disparities in Harmful Content Detection Across 50 English Dialects
DIA-HARM evaluates 16 harmful content detection models across 50 English dialects using 195K+ samples, revealing 1.4–3.6% F1 drops for fine-tuned models and up to 27% for zero-shot …
BLUFF: Benchmarking in Low-resoUrce Languages for detecting Falsehoods and Fake news
BLUFF is the largest multilingual fake news detection benchmark, spanning 79 languages with 202K+ samples. It introduces AXL-CoI for adversarial generation and mPURIFY for quality …
Chain-of-Interactions: Iterative ICL Framework for Abstractive Task-Oriented Dialogue Summarization of Conversational AI Interactions
Chain-of-Interactions (CoI) introduces a novel multi-step framework that leverages LLMs' in-context learning capabilities for abstractive task-oriented dialogue summarization. …
Graph-based Molecular In-context Learning Grounded on Morgan Fingerprints
GAMIC introduces a novel self-supervised learning approach for molecular in-context learning that combines graph neural networks with Morgan fingerprints to better capture …
ali-al-lawati
Beemo: Benchmark of Expert-edited Machine-generated Outputs
Beemo introduces a novel benchmark featuring 6.5k expert-edited machine-generated texts across diverse domains from creative writing to summarization. Through comprehensive …
ekaterina-artemova
Semantic Captioning: Benchmark Dataset and Graph-Aware Few-Shot In-Context Learning for SQL2Text
This work introduces semantic captioning for SQL queries, addressing the reverse operation of semantic parsing by translating SQL code into natural language explanations. Using …
ali-al-lawati
Authorship Obfuscation in Multilingual Machine-Generated Text Detection
This research from Penn State and KiNiT, benchmarks the effectiveness of 10 authorship obfuscation (AO) techniques against 37 machine-generated text (MGT) detection methods across …
dominik-macko