CommunityLM Example: Initial Jupyter Notebook (#15)

* Added abstract functions for LM and distmod

* Resolved type-checking error

* Resolved type-checking error

* Resolved type-checking error

* Changed distmod structure

* Everything is LM commit

* Add initial community lm example

* Remove shell check

* Fix name error

---------

Co-authored-by: Rohan Modi <rohan.modi.1028@gmail.com>

.github/workflows/ci.yml

@@ -60,11 +60,3 @@ jobs:
         uses: pre-commit/action@v3.0.0
         with:
           extra_args: check-json --all-files
-  lint-shell-script:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v3
-      - name: lint
-        uses: pre-commit/action@v3.0.0
-        with:
-          extra_args: shellcheck --all-files

.pre-commit-config.yaml

@@ -17,10 +17,6 @@ repos:
     rev: v1.34.0
     hooks:
       - id: yamllint
-  - repo: https://github.com/koalaman/shellcheck-precommit
-    rev: v0.9.0
-    hooks:
-      - id: shellcheck
   - repo: https://github.com/pre-commit/pre-commit-hooks
     rev: v4.5.0
     hooks:

examples/community_lm/.gitignore

@@ -0,0 +1,3 @@
+data/
+output/
+rankings/

examples/community_lm/README.md

@@ -0,0 +1,48 @@
+# CommunityLM
+
+This is a replication of the experiments from
+[CommunityLM](https://arxiv.org/abs/2209.07065) (Jiang et al. 2022), which
+probes partisan worldviews from language models.
+
+## Reference
+
+Some of this code and data was derived from the
+[CommunityLM repo](https://github.com/hjian42/communitylm).
+
+If you use this example, we would appreciate if you acknowledge
+[LLMents](https://github.com/neulab/llments) and the original paper.
+
+```bibtex
+@misc{
+    title = "{LLMents}: A Toolkit for Language Model Experiments",
+    author = "
+      Graham Neubig and
+      Aakriti Kinra and
+      Mihir Bansal and
+      Qingyang Liu and
+      Rohan Modi and
+      Xinran Wan
+    ",
+    year = "2024",
+    howpublished = "https://github.com/neulab/llments",
+}
+```
+
+```bibtex
+@inproceedings{jiang-etal-2022-communitylm,
+    title = "{C}ommunity{LM}: Probing Partisan Worldviews from Language Models",
+    author = "Jiang, Hang  and
+      Beeferman, Doug  and
+      Roy, Brandon  and
+      Roy, Deb",
+    booktitle = "
+      Proceedings of the 29th International Conference on Computational Linguistics
+    ",
+    month = oct,
+    year = "2022",
+    address = "Gyeongju, Republic of Korea",
+    publisher = "International Committee on Computational Linguistics",
+    url = "https://aclanthology.org/2022.coling-1.593",
+    pages = "6818--6826",
+}
+```