From 817290c02daa251b5b919fa1edbdc497f8896a40 Mon Sep 17 00:00:00 2001 From: ttstopll85 Date: Fri, 29 May 2026 11:08:41 +0800 Subject: [PATCH] Add files via upload --- .../LongContext-ICL-Annotation/src/main.py | 41 ++-- .../LongContext-ICL-Annotation/src/method.py | 226 +++++++++++++++--- .../src/requirements.txt | 17 ++ ...5\351\227\250\345\220\210\345\212\233.pdf" | Bin 0 -> 1681068 bytes 4 files changed, 240 insertions(+), 44 deletions(-) create mode 100644 openseek/competition/LongContext-ICL-Annotation/src/requirements.txt create mode 100644 "openseek/competition/LongContext-ICL-Annotation/src/\346\212\200\346\234\257\346\212\245\345\221\212-\346\264\245\351\227\250\345\220\210\345\212\233.pdf" diff --git a/openseek/competition/LongContext-ICL-Annotation/src/main.py b/openseek/competition/LongContext-ICL-Annotation/src/main.py index c2949795..42197674 100644 --- a/openseek/competition/LongContext-ICL-Annotation/src/main.py +++ b/openseek/competition/LongContext-ICL-Annotation/src/main.py @@ -4,20 +4,20 @@ # from method import build_prompt, select_examples, annotate -from method import build_prompt, select_examples +from method import build_prompt, select_examples, build_prompt_cot -from method import annotate_nvidia as annotate # For Nvidia GPU -# from method import annotate_ascend as annotate # For Huawei Ascend +# from method import annotate_nvidia as annotate # For Nvidia GPU +from method import annotate_ascend as annotate # For Huawei Ascend TASK_FILES = { - 1: './data/openseek-1_closest_integers.json', - 2: './data/openseek-2_count_nouns_verbs.json', - 3: './data/openseek-3_collatz_conjecture.json', - 4: './data/openseek-4_conala_concat_strings.json', - 5: './data/openseek-5_semeval_2018_task1_tweet_sadness_detection.json', - 6: './data/openseek-6_mnli_same_genre_classification.json', - 7: './data/openseek-7_jeopardy_answer_generation_all.json', - 8: '../data/openseek-8_kernel_generation.json', + 1: '/root/OpenSeek/openseek/competition/LongContext-ICL-Annotation/data/openseek-1_closest_integers.json', + 2: '/root/OpenSeek/openseek/competition/LongContext-ICL-Annotation/data/openseek-2_count_nouns_verbs.json', + 3: '/root/OpenSeek/openseek/competition/LongContext-ICL-Annotation/data/openseek-3_collatz_conjecture.json', + 4: '/root/OpenSeek/openseek/competition/LongContext-ICL-Annotation/data/openseek-4_conala_concat_strings.json', + 5: '/root/OpenSeek/openseek/competition/LongContext-ICL-Annotation/data/openseek-5_semeval_2018_task1_tweet_sadness_detection.json', + 6: '/root/OpenSeek/openseek/competition/LongContext-ICL-Annotation/data/openseek-6_mnli_same_genre_classification.json', + 7: '/root/OpenSeek/openseek/competition/LongContext-ICL-Annotation/data/openseek-7_jeopardy_answer_generation_all.json', + 8: '/root/OpenSeek/openseek/competition/LongContext-ICL-Annotation/data/openseek-8_kernel_generation.json', } def parser_args(): @@ -30,7 +30,7 @@ def parser_args(): default='../outputs/', help='Prefix path to save the evaluation logs.') parser.add_argument('--tokenizer_path', type=str, - default='/share/project/wuhaiming/spaces/data_agent/OpenSeek-main/openseek/competition/LongContext-ICL-Annotation/src/Qwen3-4B') + default='/root/Qwen3-4B') args = parser.parse_args() return args @@ -48,7 +48,7 @@ def evaluate(task_id:int, task_name = task_dict['task_name'] task_description = task_dict['Definition'][0] - icl_examples = task_dict['examples'][:100] + icl_examples = task_dict['examples'][:50] test_samples = task_dict['test_samples'] version = 1 @@ -70,7 +70,16 @@ def evaluate(task_id:int, text2annotate = test_sample['input'] - prompt = build_prompt(task_description, text2annotate) + + # Use CoT prompt for Task 3 and 4, standard prompt for others (Account 3 strategy) + # Task 3: Collatz conjecture (math reasoning) - CoT helps + # Task 4: String concatenation - CoT significantly helped in Account 2 (+29.2%) + # Task 8: Kernel generation - CoT was harmful in Account 2 (6.0% -> 0.6%) + if task_id in [3, 4]: + prompt = build_prompt_cot(task_description, text2annotate, task_id) + else: + prompt = build_prompt(task_description, text2annotate) + if examples_str is None: examples_str = select_examples(icl_examples, task_description, text2annotate) input_prompt = prompt.replace("[[EXAMPLES]]\n\n", examples_str+'\n\n') @@ -79,9 +88,9 @@ def evaluate(task_id:int, # if tokenized_input['input_ids'].shape[1] > max_input_length: # test_record['prediction'] = None # else: - # prediction = annotate(input_prompt) + # prediction = annotate(input_prompt, task_id) # test_record['prediction'] = prediction - prediction = annotate(input_prompt) + prediction = annotate(input_prompt, task_id) test_record['prediction'] = prediction with open(output_file, 'a') as f: f.write(json.dumps(test_record)+'\n') diff --git a/openseek/competition/LongContext-ICL-Annotation/src/method.py b/openseek/competition/LongContext-ICL-Annotation/src/method.py index 386daf22..f093453b 100644 --- a/openseek/competition/LongContext-ICL-Annotation/src/method.py +++ b/openseek/competition/LongContext-ICL-Annotation/src/method.py @@ -49,6 +49,7 @@ def build_prompt____(task_description: str, text2annotate: str) -> str: def build_prompt(task_description: str, text2annotate: str) -> str: """ Construct a high-precision prompt for long-context data annotation (optimized for Qwen3-4B). + M01 优化版本：严格标签输出稳态方案 task_description: Clear description of the annotation task (e.g., "Classify English product reviews as Good Review/Bad Review"). text2annotate: The text to be annotated (single text or batch texts). """ @@ -60,17 +61,28 @@ def build_prompt(task_description: str, text2annotate: str) -> str: "### Core Task\n" f"{task_description}\n\n" - "### Critical Annotation Guidelines\n" - "1. **Example Learning Requirement**: Thoroughly analyze and fully learn from the annotation logic, format, and criteria in the Examples section. " - "Your annotation must align with the style, judgment standards, and tag usage shown in the examples.\n" - "2. **Thinking Process**: You may (and are encouraged to) explain your annotation reasoning step by step (e.g., key information extraction, judgment basis, rule matching).\n" - "3. **Mandatory Output Rule**: Regardless of any thinking process you provide, your final annotation result MUST be enclosed in \n" - "4. **Length Adaptation**: For long texts, maintain complete thinking process and ensure the final