Temporal Simultaneity Predicts Annotation Quality in Setswana Sentiment Corpora
Researchers present a Setswana sentiment dataset of 3,565 tweets annotated by three native speakers across eight batches, finding that inter-annotator agreement (IAA) declines sharply over time despite an aggregate Kappa of 0.76. The dominant predictor of agreement quality is temporal simultaneity: tweets labeled within one minute achieve κ=0.98 versus κ=0.65 for those labeled more than a day apart. The study also benchmarks multilingual encoders and proprietary models including GPT-5 and Gemini on three-class sentiment classification, with GPT-5 few-shot achieving the best result at 62.2 macro-F1. The dataset, timestamps, and analysis code are released to support reproducible quality auditing for African language NLP.
Related guides (3)
Related events (8)
WhoSaidIt: Human-LLM Collaborative Annotation for Multilingual Speaker-Attribute Classification
This paper proposes a human-LLM collaborative re-annotation framework for stabilizing noisy multilingual speaker-attribute labels under resource constraints. LLMs surface recurring annotation rationales through iterative expert interaction, combined with disagreement-focused sampling for targeted re-annotation. The resulting WhoSaidIt dataset covers nine speaker-attribute labels across multiple languages. Benchmarking of recent LLMs reveals substantial cross-lingual annotation divergence and highlights both capabilities and limitations of LLMs in this classification task.
Text Analytics Evaluation Framework: Benchmarking LLMs on Social Media NLP Tasks
Researchers introduce a 470-question evaluation framework to assess LLM performance on aggregated social media text, applied to Twitter datasets across sentiment analysis, hate speech detection, and emotion recognition. Results show performance degrades substantially as input scale exceeds 500 instances, particularly for open-weights models on numerical tasks. Multi-label and target-dependent scenarios also show notable performance drops, and task complexity progressively erodes accuracy from basic semantic identification to comparison and counting operations. The findings point to architectural bottlenecks in current LLMs for rigorous quantitative analysis over large text collections.
Temporally Ordered Pre-training Improves LLM Factual Freshness (Kairos)
Researchers from Kyutai pre-train 6B-parameter models on temporally ordered Common Crawl snapshots and compare them against standard shuffled pre-training baselines. They introduce a benchmark of over 7,000 temporally grounded questions to evaluate whether models correctly associate facts with their corresponding time periods. Results show sequentially trained models match shuffled baselines on general language understanding while exhibiting more up-to-date and temporally precise factual knowledge. Code, checkpoints, and datasets are released under the Kairos project.
Annotated dataset for enthymeme detection in political tweets with disagreement-aware training
Researchers present a dataset of 1,482 politically controversial tweets annotated by five annotators for enthymemes — arguments with unstated premises or conclusions — designed to study label variation rather than eliminate it. Annotation guidelines are grounded in Walton's argumentation schemes, and the paper includes a complexity analysis of cognitive load in the task. Preliminary experiments show that models trained on annotator disagreement outperform those trained on hard majority-vote labels, suggesting value in preserving annotation disagreement for subjective NLP tasks.
Sentence-Level Clinical Provenance Categorization for Multidisciplinary Hospital Summarization Using Fine-Tuned Llama-3
This pilot study presents a pipeline for categorizing sentence-level clinical provenance across multi-source hospital notes, targeting structured summarization in high-complexity settings like the NICU. The authors fine-tune Llama-3 8B and 70B models on MedSecId (MIMIC-III annotations), achieving Macro F1 above 92% in-domain. Cross-domain evaluation reveals a scale-dependent transfer effect: SFT substantially improves the 70B model (+7% Macro F1) but yields only marginal gains for the 8B model. A quantized fine-tuned 70B model outperforms its full-precision baseline while reducing compute, suggesting quantized adaptation is viable for structured clinical NLP tasks.
Moment-Video: Benchmark Diagnosing Temporal Fidelity of Video MLLMs on Momentary Visual Events
Moment-Video is a new benchmark of 1,000 human-verified video-QA pairs designed to evaluate how well video multimodal large language models (MLLMs) handle brief, localized visual events that may span only a few frames. The benchmark covers 7 domains and 25 subcategories across four task types: Temporal Occurrence, Temporal Counting, Action Description, and Temporal Reasoning. Evaluation of 33 proprietary and open-source models reveals severe deficiencies: the best model (Seed-2.0-Pro) achieves only 39.6% accuracy, while most open-source models score below 25%. Diagnostic analyses show that denser frame sampling helps but does not resolve the bottleneck, pointing to fundamental limitations in how current video MLLMs represent and preserve transient visual evidence.
Interaction SSD: Modeling Annotator Identity Effects on Hate Speech Semantic Gradients
This paper introduces Interaction SSD, an extension of Supervised Semantic Differential that tests how semantic meaning varies across moderating variables such as annotator group identity. Applied to the UC Berkeley Measuring Hate Speech corpus, the method detects that annotator racial identity significantly moderates hate-speech judgments, with a shared gradient distinguishing dehumanizing hostility from counter-speech and an interaction gradient revealing group-linked differences in predictive semantic cues. The approach makes moderated meaning-outcome relationships statistically testable and interpretable through standard SSD tooling.
Calibrated LLM annotation and encoder transfer for measuring human values in social media text
A new arXiv preprint investigates how different LLMs, prompts, and instruction languages operationalize Schwartz's theory of basic human values when annotating non-English social media posts. The authors evaluate annotation quality beyond standard F1 metrics, examining structural alignment, error structure, and confidence-ambiguity relations, finding that iterative prompt calibration reduces misattributions. They also demonstrate that LLM annotations can be transferred to a smaller encoder model via soft-label training, preserving theory-grounded value interpretations and uncertainty information.