Merge pull request #226 from jon-tow/evaluator-description-option

Replace `fewshot_description` API with a `description_dict` based interface

lm_eval/tasks/lambada_cloze.py

@@ -13,6 +13,3 @@ class LAMBADA_cloze(LAMBADA):
 
     def doc_to_target(self, doc):
         return " " + doc['text'].rsplit(' ', 1)[1]
-    
-    def fewshot_description(self):
-        return "Fill in blank:\n"

lm_eval/tasks/logiqa.py

@@ -80,9 +80,5 @@ class LogiQA(MultipleChoiceTask):
     def test_docs(self):
         return self._load_docs(self.DATASET_PATH / "Test.txt")
 
-    def fewshot_description(self):
-        # TODO: figure out actual description
-        return ""
-
     def doc_to_text(self, doc):
         return doc["query"]

lm_eval/tasks/mathqa.py

@@ -29,9 +29,5 @@ class MathQA(HFTask, MultipleChoiceTask):
         }
         return out_doc
 
-    def fewshot_description(self):
-        # TODO: figure out description
-        return ""
-
     def doc_to_text(self, doc):
         return doc["query"]

lm_eval/tasks/mc_taco.py

@@ -39,9 +39,6 @@ class MCTACO(HFTask):
     def has_test_docs(self):
         return True
 
-    def fewshot_description(self):
-        return "Determine whether the candidate answer is plausible (\"yes\") or not (\"no\")"
-
     def doc_to_text(self, doc):
         return f"{doc['sentence']}\nQuestion: {doc['question']}\n"\
             f"Answer: {doc['answer']}\nPlausible:"

lm_eval/tasks/mutual.py

@@ -70,10 +70,6 @@ class MuTualBase(Task):
     def test_docs(self):
         return NotImplemented
 
-    def fewshot_description(self):
-        # TODO: figure out fewshot description
-        return ""
-
     def doc_to_text(self, doc):
         return self.detokenize(doc["article"])
 

lm_eval/tasks/naturalqs.py

@@ -21,10 +21,6 @@ class NaturalQs(HFTask):
     def has_test_docs(self):
         return False
 
-    def fewshot_description(self):
-        # TODO: figure out description
-        return ""
-
     def training_docs(self):
         # Cache training for faster few-shot.
         # Data is too large to fit in memory.

lm_eval/tasks/openbookqa.py

@@ -25,9 +25,5 @@ class OpenBookQA(HFTask, MultipleChoiceTask):
         }
         return out_doc
 
-    def fewshot_description(self):
-        # TODO: figure out fewshot description
-        return ""
-
     def doc_to_text(self, doc):
         return doc["query"]

lm_eval/tasks/piqa.py

@@ -18,10 +18,6 @@ class PiQA(HFTask, MultipleChoiceTask):
     def has_test_docs(self):
         return False
 
-    def fewshot_description(self):
-        # TODO: figure out fewshot description
-        return ""
-
     def _convert_standard(self, doc):
         out_doc = {
             "goal": doc["goal"],

lm_eval/tasks/prost.py

@@ -36,13 +36,14 @@ class PROST(HFTask, MultipleChoiceTask):
     def has_test_docs(self):
         return True
 
-    def fewshot_description(self):
-        # TODO: figure out fewshot description
-        return ""
-
-    def fewshot_context(self, doc, num_fewshot, provide_description, rnd):
+    def fewshot_context(self, doc, num_fewshot, provide_description=None, rnd=None, description=None):
         assert num_fewshot == 0, 'PROST is designed to probe models in a zero-shot fashion only.'
-        return super().fewshot_context(doc, num_fewshot, provide_description, rnd)
+        return super().fewshot_context(
+            doc=doc,
+            num_fewshot=num_fewshot,
+            rnd=rnd,
+            description=description
+        )
 
     def _convert_standard(self, doc):
         out_doc = {

lm_eval/tasks/pubmedqa.py

@@ -23,11 +23,6 @@ class Pubmed_QA(HFTask):
             # HF is labelled as train but its really just for testing
             return self.data["train"]
 
-    def fewshot_description(self):
-        # Average ctx length in labelled dataset is 238.9
-        # 2 few-shot exmamples pushes it beyond context window
-        return ""
-
     def doc_to_text(self, doc):
         ctxs = "\n".join(doc["context"]["contexts"])
         return "Abstract: {}\nQuestion: {}\nAnswer:".format(

lm_eval/tasks/qa4mre.py

@@ -67,9 +67,6 @@ class QA4MRE(MultipleChoiceTask):
                 out_doc['source'] = src
                 yield out_doc
 
-    def fewshot_description(self):
-        return ""
-
     def test_docs(self):
         return self.load_docs(f"data/qa4mre/QA4MRE-{self.YEAR}-EN_GS.xml")
 

lm_eval/tasks/quac.py

@@ -51,11 +51,6 @@ class QuAC(Task):
     def test_docs(self):
         raise NotImplementedError("QuAC has no test docs.")
     
-    def fewshot_description(self):
-        # TODO: figure out fewshot description
-        desc = "TITLE: Title of the context passage - subtitle of the passage\nPARAGRAPH: Passage describing the relevant information for answering questions.\n\nQ: Text of a question.\n\nA: Answer to the question, based on the passage. If it cannot be answered based on the passage, write CANNOTANSWER"
-        return desc
-
     def load_doc(self, myjson):
         docs = []
         for item in myjson:

lm_eval/tasks/race.py

@@ -65,10 +65,6 @@ class RACE(HFTask):
     def test_docs(self):
         return self._collate_data("test")
 
-    def fewshot_description(self):
-        # TODO: figure out description
-        return ""
-
     @classmethod
     def get_answer_option(cls, problem):
         answer = cls.letter_to_num[problem['answer']]

lm_eval/tasks/sat.py

@@ -61,10 +61,5 @@ class SATAnalogies(MultipleChoiceTask):
             }
             yield doc
 
-    
-    def fewshot_description(self):
-        # TODO: figure out actual description
-        return ""
-
     def doc_to_text(self, doc):
         return "{} is to {} as".format(*doc['query'])

lm_eval/tasks/sciq.py

@@ -50,9 +50,6 @@ class SciQ(MultipleChoiceTask):
         for record in docs:
             yield self._convert_standard(record)
 
-    def fewshot_description(self):
-        return ""
-
     def training_docs(self):
         return self.load_docs("data/sciq/SciQ dataset-2 3/train.json")
 

lm_eval/tasks/squad.py

@@ -41,10 +41,6 @@ class SQuAD2(HFTask):
     def validation_docs(self):
         return self.data["validation"]
 
-    def fewshot_description(self):
-        # TODO: figure out description
-        return ""
-
     def doc_to_text(self, doc):
         return 'Title: ' + doc['title'] + '\n\n' + 'Background: ' + doc['context'] + '\n\n' + 'Question: ' + doc['question'] + '\n\n' + 'Answer:'
 

lm_eval/tasks/storycloze.py

@@ -27,18 +27,12 @@ class StoryCloze(Task):
             filereader = csv.reader(file)
             return list(filereader)
                 
-
     def validation_docs(self):
         return self.load_doc("data/storycloze/cloze_test_val__winter2018-cloze_test_ALL_val - 1 - 1.csv")
 
     def test_docs(self):
         return self.load_doc("data/storycloze/cloze_test_test__winter2018-cloze_test_ALL_test - 1.csv")
 
-    
-    def fewshot_description(self):
-        # TODO: figure out fewshot description
-        return ""
-    
     def doc_to_text(self, doc):
         return ' '.join([*doc[1:5]])
 

lm_eval/tasks/superglue.py

@@ -26,10 +26,6 @@ class BoolQ(HFTask):
     def has_test_docs(self):
         return False
 
-    def fewshot_description(self):
-        # TODO: figure out actual description
-        return "Read the following passages and answer each question with a yes or a no."
-
     def doc_to_text(self, doc):
         return f"{doc['passage']}\nQuestion: {doc['question']}?\nAnswer:"
     
@@ -78,11 +74,6 @@ class CommitmentBank(HFTask):
     def has_test_docs(self):
         return False
 
-    def fewshot_description(self):
-        # TODO: figure out actual description
-        return "Given a premise and a hypothesis, classify whether the author of the premise is committed" \
-            "to the truth of the hypothesis. The three possible labels are true, false or neither."
-
     def doc_to_text(self, doc):
         return "{}\nQuestion: {}. True, False or Neither?\nAnswer:".format(
             doc["premise"],
@@ -150,11 +141,6 @@ class Copa(HFTask):
     def has_test_docs(self):
         return False
 
-    def fewshot_description(self):
-        # TODO: figure out actual description
-        return "Given a premise and one alternative with a causal relation to the premise and another without," \
-            "choose the more plausible alternative"
-
     def doc_to_text(self, doc):
         # Drop the period
         connector = {
@@ -215,10 +201,6 @@ class MultiRC(HFTask):
     def has_test_docs(self):
         return False
 
-    def fewshot_description(self):
-        # TODO: figure out actual description
-        return "READING COMPREHENSION ANSWER KEY"
-
     def doc_to_text(self, doc):
         return f"{doc['paragraph']}\nQuestion: {doc['question']}\nAnswer:"
 
@@ -270,10 +252,6 @@ class ReCoRD(HFTask):
     def has_test_docs(self):
         return False
 
-    def fewshot_description(self):
-        # TODO: figure out actual description
-        return ""
-
     def training_docs(self):
         # In ReCoRD, each doc manifests multiple "examples" in the context of few shot example packing.
         # Each doc consists of multiple answer candidates, each of which is scored yes/no.
@@ -363,10 +341,6 @@ class WordsInContext(HFTask):
     def has_test_docs(self):
         return False
 
-    def fewshot_description(self):
-        # TODO: figure out actual description
-        return ""
-
     def doc_to_text(self, doc):
         return "Sentence 1: {}\nSentence 2: {}\nQuestion: Is the word '{}' used in the same way in the" \
                " two sentences above?\nAnswer:".format(
@@ -432,12 +406,6 @@ class SGWinogradSchemaChallenge(HFTask):
                 ]
             return self._training_docs
 
-    def fewshot_description(self):
-        return "Final Exam with Answer Key\n" \
-           "Instructions: Please carefully read the following passages. " \
-           "For each passage, you must identify which noun the pronoun marked in *bold*" \
-           " refers to.\n====="
-
     def doc_to_text(self, doc):
         raw_passage = doc["text"]
         # NOTE: HuggingFace span indices are word-based not character-based.

lm_eval/tasks/translation.py

@@ -166,12 +166,6 @@ class GeneralTranslationTask(Task):
             "ter": False,
         }
 
-    def fewshot_description(self):
-        language_codes = self.sacrebleu_language_pair.split("-")
-        src_lang = code_to_language(language_codes[0])
-        tar_lang = code_to_language(language_codes[1])
-        return f"Translate these {src_lang} phrases to {tar_lang}."
-
     def __str__(self):
         language_codes = self.sacrebleu_language_pair.split("-")
         src_lang = code_to_language(language_codes[0])

lm_eval/tasks/triviaqa.py

@@ -36,10 +36,6 @@ class TriviaQA(Task):
     def test_docs(self):
         raise NotImplementedError()
     
-    def fewshot_description(self):
-        # TODO: figure out fewshot description
-        return ""
-    
     def doc_to_text(self, doc):
         return f"Question: {doc['Question']}\nAnswer:"
 
@@ -57,7 +53,6 @@ class TriviaQA(Task):
 
         return ret
 
-
     def construct_requests(self, doc, ctx):
         ret = []
         for alias in self._remove_prefixes(doc['Answer']['Aliases']):