Add paper and project page links

#1
by nielsr HF Staff - opened
Files changed (1) hide show
  1. README.md +9 -5
README.md CHANGED
@@ -1,12 +1,12 @@
1
  ---
2
- license: apache-2.0
 
 
3
  language:
4
  - en
5
  library_name: transformers
 
6
  pipeline_tag: text-classification
7
- base_model: google-bert/bert-base-uncased
8
- datasets:
9
- - hotpotqa/hotpot_qa
10
  tags:
11
  - prompt-compression
12
  - dependency-detection
@@ -20,6 +20,10 @@ This is the sentence-pair dependency detector released with **Relevant but
20
  Incomplete: Referential Dangling as a Paradigm-Level Failure Mode in Hard
21
  Prompt Compression**.
22
 
 
 
 
 
23
  The model scores whether a candidate sentence supplies a necessary dependency
24
  for a retained sentence, conditioned on the question. It is used by the
25
  repository's automatic context-restoration experiments.
@@ -97,4 +101,4 @@ languages, or substantially different compression settings without evaluation.
97
  author={Zhengpei Hu and Kai Li and Dapeng Fu and Xuechao Zou and Yuanhao Tang and Yue Li and Tengfei Cao and Jianqiang Huang},
98
  note={Research code and model release}
99
  }
100
- ```
 
1
  ---
2
+ base_model: google-bert/bert-base-uncased
3
+ datasets:
4
+ - hotpotqa/hotpot_qa
5
  language:
6
  - en
7
  library_name: transformers
8
+ license: apache-2.0
9
  pipeline_tag: text-classification
 
 
 
10
  tags:
11
  - prompt-compression
12
  - dependency-detection
 
20
  Incomplete: Referential Dangling as a Paradigm-Level Failure Mode in Hard
21
  Prompt Compression**.
22
 
23
+ **Paper:** [Relevant but Incomplete: Referential Dangling as a Paradigm-Level Failure Mode in Hard Prompt Compression](https://huggingface.co/papers/2608.04569)
24
+
25
+ **Project page:** [https://cslikai.cn/Referential-Dangling/](https://cslikai.cn/Referential-Dangling/)
26
+
27
  The model scores whether a candidate sentence supplies a necessary dependency
28
  for a retained sentence, conditioned on the question. It is used by the
29
  repository's automatic context-restoration experiments.
 
101
  author={Zhengpei Hu and Kai Li and Dapeng Fu and Xuechao Zou and Yuanhao Tang and Yue Li and Tengfei Cao and Jianqiang Huang},
102
  note={Research code and model release}
103
  }
104
+ ```