Open access · No fees · Permanent links
Share your research with the world — free, forever
An open repository for papers, preprints, datasets, theses and more. Every upload gets a permanent link, a ready-made citation and metadata that Google Scholar can read.
Browse: Journal articles Datasets Preprints By date
- Records
- 111
- Researchers
- 13
- Downloads
- 1,487
- Views
- 972
- Open access, alwaysFree to read and download, with no paywall and no reader account.
- Permanent linksA stable identifier like LOR-00042 and a URL that never changes.
- Ready citationsAPA and BibTeX on every record, copied in one click.
- Scholar-ready metadataHighwire, Dublin Core, schema.org and OAI-PMH for indexes and harvesters.
Recently published
Browse all-
Journal article
Who Spoke Next Is Not Who Should Have: What Zero-Shot Failure on Multi-Party Turn-Taking Benchmarks Measures, Why the Human Reference Sits Beside the Models, and What Would Show That Knowing When to Speak Must Be Trained
An assistant that joins a group conversation has to decide, at every pause, whether to take the floor. Two 2026 benchmarks report that language models prompted zero-shot make this decision badly and that fine-tuning repairs it, and both conclude that knowing when to speak is learned…
-
Journal article
A Rewrite That Keeps the Label Has Already Read It: Why an LLM Paraphrase Can Raise a Sentiment Classifier's Accuracy Without the Classifier Getting Better, Four Accounts of the Gain, and the Re-Annotation and Neutral-Rate Controls That Would Separate Them
A 2026 study reports that sentiment classifiers score higher on reviews rewritten by small language models than on the human originals, by up to 5.8 accuracy points, and reads the gain as stylistic alignment: the rewrite strips idiosyncrasy and hands the classifier text closer to what it…
-
Journal article
Which Signal Did the Synthesis Import? Information, Re-presentation and Selection in Synthetic Pretraining, Why 'the Verifier Is Doing the Work' Holds Only Where Correctness Is the Target, and the Controls That Would Assign the Credit
The expectation that language models will keep improving after the supply of human text runs out rests on a claim about synthetic data: that a model, or a family of models, can produce training text worth more than the text it was trained on. A competing reading holds that no…
-
Journal article
Robust Because Coarse, or Robust Because Planned? A Research Agenda for Training-Data Provenance After the Aggregate-Disclosure Turn, in Which Granularity Buys Statistical Power, Prior Randomisation Buys Soundness, and Per-Example Value Has Neither
Regulators have chosen coarse disclosure of training data: the template for the EU AI Act's public summary of training content asks for lists of large datasets, a summary of the most relevant crawled domains and a description of how opt-outs were honoured, and does not require a list of…
-
Journal article
A Blind Score Is Not a Reliance Measure: What Answering Without the Audio Shows About Audio-Language Benchmarks, Why the Partial-Input Debate Already Settled Half of It, and the Counterfactual-Audio Test the Other Half Needs
Audio-language models are now routinely tested with the audio taken away, and the results are read in opposite directions. One 2026 audit reports that eight models keep 60 to 72 percent of their accuracy on three benchmarks when the audio is omitted, and concludes that the scores largely…
-
Journal article
Lossless at What Length? Near-Lossless KV Cache Compression Is a Claim Indexed by Decode Exposure, Scoring Statistic and Budget Accounting, the Decode-Aware Line Has Answered the First Index Mostly on Final-Answer Accuracy, and Divergence From the Full Cache Is Not by Itself the Defect
Key-value cache compression is routinely reported as near-lossless at aggressive budgets: eviction, quantisation and merging methods keep a fifth or a tenth of the cache and match the full-cache score. A 2025-2026 line of work argues that the result was manufactured by evaluation…
Browse by research type
Archive by dateTrending this month
More popular research →Popular subjects
All subjects A–Z →Guides for researchers
All 8 guides →How to deposit your research on Life of Research, step by step
Every field of the deposit form explained, from abstract to file order, and what happens after you press Publish.
Getting found and citedHow to get your research indexed in Google Scholar
The technical rules Google Scholar applies, the usual reasons a paper never appears, and a checklist before you deposit.
Getting found and citedHow to cite a dataset, software and a preprint, with worked examples
Copyable APA and BibTeX patterns for data, code and preprints, with the version and identifier details people forget.
How scholarly publishing worksOpen access explained: green, gold and diamond
Green, gold, diamond, hybrid and bronze compared: who pays, which version is free, and what you may share.
How it works
- 1
Create a free account
Takes under a minute. No fees, no review queues, no institutional login needed.
- 2
Upload & describe
Drop in your PDF or dataset. Paste a DOI and the title, authors and journal fill themselves in.
- 3
Share your permanent link
Every record gets a stable identifier, a citation in APA & BibTeX, and Google Scholar-ready metadata.
Your work deserves a permanent home
Independent researchers, students and labs use Life of Research to make their papers, data and code findable and citable.