rbroc echo issues - Githubissues

rbroc / echo

A Scalable and Explainable Approach to Discriminating Between Human and Artificially Generated Text

https://cc.au.dk/en/clai/current-projects/a-scalable-and-explainable-approach-to-discriminating-between-human-and-artificially-generated-text

2 stars 1 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

minor clean: delete rogue file

#69 MinaAlmasi closed 2 days ago
0
Refactoring: Small fixes to utils to ensure old code works + newer (prettier) tables

#68 MinaAlmasi closed 5 days ago
0
small fixes, docs to classify

#67 MinaAlmasi closed 1 week ago
0
Classify pipeline

#66 MinaAlmasi closed 1 week ago
0
Dropping raw features with many zero values prior to PCA?

#65 MinaAlmasi opened 2 weeks ago
0
Classify: Fix filtering lengths and identification of NA features

#64 MinaAlmasi closed 2 weeks ago
0
fix classify pipeline: prelim results on all PC comps

#63 MinaAlmasi closed 2 weeks ago
0
Computing Perplexity outside of TextDescriptives (and Entropy)

#62 MinaAlmasi opened 2 weeks ago
1
Refactoring: Weird steps in the pipeline (cleaning at various steps that could be streamlined)

#61 MinaAlmasi opened 3 weeks ago
0
Preliminary Classification Pipeline

#59 MinaAlmasi closed 4 months ago
0
DailyDialog: regenerate + extract new metrics

#58 MinaAlmasi closed 4 months ago
0
METRICS EXTRACTION + PERFORMANCE: Created one pipeline for standardising the extraction of both AI and human metrics + performance update.

#57 MinaAlmasi closed 4 months ago
0
DailyDialog: Regenerate dataset with correct lengths + extract new metrics for it

#56 MinaAlmasi closed 4 months ago
0
spring cleaning: adding documentation, removing old code, trim down folders

#55 MinaAlmasi closed 5 months ago
0
Preliminary analysis (checking lengths, PCA on simple features)

#54 MinaAlmasi closed 5 months ago
0
features quantifying overlap / relation between source and completion

#53 rbroc opened 5 months ago
0
flag weird model-generated text

#52 rbroc closed 2 months ago
0
add stories 22 data for llama7b

#50 MinaAlmasi closed 6 months ago
0
Finish generations of data (for now!)

#49 MinaAlmasi closed 6 months ago
0
Final Prompts + Generation of Data

#48 MinaAlmasi closed 6 months ago
0
Landing on prompts

#47 MinaAlmasi closed 5 months ago
1
Clean human data for better model prompts

#46 MinaAlmasi closed 6 months ago
0
Human Data Cleaning: reformatting speakers in DailyDialog + inspect other human data

#45 MinaAlmasi closed 6 months ago
0
dailymail_cnn: weird cleaning or weird formatting?

#44 MinaAlmasi opened 6 months ago
7
Exploring Data BonusInfo in

#43 MinaAlmasi closed 6 months ago
0
Generating data with vLLM (generations + hacky fix to min tokens)

#41 MinaAlmasi closed 7 months ago
0
Minor update: Add temperature as CLI arg + add all sample params as dict in df col for generations

#40 MinaAlmasi closed 7 months ago
0
Dailydialog: Re-introduce [EOT] tokens as alternating speaker 1 and speaker 2 (+ general streamlining of data cleaning)

#39 MinaAlmasi closed 7 months ago
0
vLLM implementation

#38 MinaAlmasi closed 7 months ago
0
Fix Quantized Mdl Implementation, add probabilistic decoding, streamline generate scripts

#37 MinaAlmasi closed 7 months ago
0
Docs: Add more content to readme

#36 MinaAlmasi closed 9 months ago
0
MORE refactoring

#35 MinaAlmasi closed 9 months ago
0
(MINOR) restructuring/cleaning of repo

#34 MinaAlmasi closed 9 months ago
0
INTERACTIVE PLOTS + MODIFIED GEN PIPELINE

#33 MinaAlmasi closed 9 months ago
0
data cleanup before fitting models

#32 rbroc opened 10 months ago
1
PROMPT SELECTION: RESULTS README

#31 MinaAlmasi closed 10 months ago
0
PROMPT SELECTION: pca, euclidean distances

#30 MinaAlmasi closed 10 months ago
0
PRELIM: implement distance function in n-dimensions for PCA data

#29 MinaAlmasi closed 10 months ago
0
FIX PCA PLOTS

#28 MinaAlmasi closed 10 months ago
0
add prelim PCA results, add PCA script

#27 MinaAlmasi closed 10 months ago
0
BELUGA and LLAMA2chat example generations (all datasets, all prompts)

#26 MinaAlmasi closed 10 months ago
0
add llama completions

#25 MinaAlmasi closed 11 months ago
0
ditching foundation models

#24 rbroc opened 11 months ago
0
Fix bottleneck in GPU performance (pipeline batching)

#23 MinaAlmasi closed 12 months ago
0
Optimise performance

#22 MinaAlmasi closed 12 months ago
0
PROMPTING: More stable prompting, chat versions implemented, one-shot testing,

#21 MinaAlmasi closed 12 months ago
0
PROMPTING: more complete prompt pipeline, implementing models, some data cleaning

#20 MinaAlmasi closed 1 year ago
0
Add prelim gen pipeline, fix some cleaning

#19 MinaAlmasi closed 1 year ago
0
solve falcon dependency issues

#18 rbroc closed 1 year ago
0
Extract textdescriptives metrics

#17 rbroc closed 1 year ago
0