The Surprising Performance of Simple Baselines for Misinformation\n Detection
Bibliographic record
Abstract
As social media becomes increasingly prominent in our day to day lives, it is\nincreasingly important to detect informative content and prevent the spread of\ndisinformation and unverified rumours. While many sophisticated and successful\nmodels have been proposed in the literature, they are often compared with older\nNLP baselines such as SVMs, CNNs, and LSTMs. In this paper, we examine the\nperformance of a broad set of modern transformer-based language models and show\nthat with basic fine-tuning, these models are competitive with and can even\nsignificantly outperform recently proposed state-of-the-art methods. We present\nour framework as a baseline for creating and evaluating new methods for\nmisinformation detection. We further study a comprehensive set of benchmark\ndatasets, and discuss potential data leakage and the need for careful design of\nthe experiments and understanding of datasets to account for confounding\nvariables. As an extreme case example, we show that classifying only based on\nthe first three digits of tweet ids, which contain information on the date,\ngives state-of-the-art performance on a commonly used benchmark dataset for\nfake news detection --Twitter16. We provide a simple tool to detect this\nproblem and suggest steps to mitigate it in future datasets.\n
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.011 | 0.034 |
| Meta-epidemiology (narrow) | 0.005 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.006 | 0.004 |
| Science and technology studies | 0.002 | 0.002 |
| Scholarly communication | 0.004 | 0.010 |
| Open science | 0.004 | 0.003 |
| Research integrity | 0.005 | 0.005 |
| Insufficient payload (model declined to judge) | 0.004 | 0.009 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".