-
For example, here: https://africanlii.org/indexes/case-indexes/case-indexes-human-rights?jurisdictions=African%20Regional%20Bodies&q=&sort=-date
under each judgment, I would like to see the terms the…
-
### Link to the coursework
https://applymagicsauce.com/demo
### Why are we doing this?
Companies are very interested in the data provided by software like Apply Magic Sauce. Automated languag…
-
Did you use a special validation set for ultrafeedback when tuning the hyper-paramaters in Table 7, or just the `test_pref` set from the [original binarized ultrafeedback data](https://huggingface.co/…
-
- [ ] [[2303.16634] G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://arxiv.org/abs/2303.16634)
# [2303.16634] G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment
…
-
# What makes a good conversation? How controllable attributes affect human judgments
「良い対話システムとは何か?」について、モデルによる出力制御と人手評価の関係性を調査した研究。出力制御では、次の4つの項目について制御を行なった: 応答の繰り返し, 応答の具体性, 発話と応答の関係性, 質問と応答のバランス。結…
-
# URL
- https://arxiv.org/pdf/2408.02666
# Affiliations
- Tianlu Wang, N/A
- Ilia Kulikov, N/A
- Olga Golovneva, N/A
- Ping Yu, N/A
- Weizhe Yuan, N/A
- Jane Dwivedi-Yu, N/A
- Richard Yu…
-
Hi,
Thanks for the super cool work. Do you plan to release the evaluation dataset? (with human judgments)
-
@zhangmozhi In your ACL paper you've discussed human generations and human judgments.
Wondering if any of these are available online?
FYI @Palipoor
-
### Author Pages
https://aclanthology.org/people/f/fei-liu/
https://aclanthology.org/people/f/fei-liu-utdallas/
### Type of Author Metadata Correction
- [X] The author page wrongly conflates diffe…
-
The idea would be to build and run a benchmark with at least the following datasets: [HHH Alignment](https://huggingface.co/datasets/HuggingFaceH4/hhh_alignment) & [MT Bench Human Judgment](https://hu…