2nd/10_Wiki/Topics/AI_and_ML/Dynamic Few-Shot (동적 퓨샷 선택 전략).md

id, title, category, status, canonical_id, aliases, duplicate_of, source_trust_level, confidence_score, verification_status, tags, raw_sources, last_reinforced, github_commit, tech_stack

id	title	category	status	canonical_id	aliases	duplicate_of	source_trust_level	confidence_score	verification_status	tags	raw_sources	last_reinforced	github_commit	tech_stack
wiki-2026-0508-dynamic-few-shot	Dynamic Few-Shot Selection	10_Wiki/Topics	verified	self	dynamic few-shot in-context learning ICL retrieval RAG few-shot kNN-prompting	none	A	0.9	applied	prompt-engineering few-shot in-context-learning rag vector-search llm retrieval		2026-05-10	pending	language framework Python LangChain / LlamaIndex / Faiss / Chroma

Dynamic Few-Shot

매 한 줄

"매 static example 의 X — 매 query-similar example 의 retrieve". 매 RAG-style example pool. 매 매 input 의 most relevant N example 의 inject. 매 modern: 매 hybrid (BM25 + dense) + 매 diversity rerank + 매 LLM-as-judge selection.

매 핵심

매 motivation

• Static: 매 매 prompt 의 같은 example.
• Dynamic: 매 매 query 의 best match.
• Result: 매 accuracy ↑ + 매 token 의 efficient.

매 selection strategy

Similarity-based

• 매 cosine on embedding.
• 매 top-K nearest.

Diversity (MMR)

• 매 redundancy ↓.
• 매 broader coverage.

LLM-as-judge

• 매 first retrieve N → 매 LLM 의 best K.
• 매 expensive but high-quality.

Skill / category-based

• 매 query 의 type 의 classify → 매 type-specific example.

Iterative refinement

• 매 매 round 의 example 의 update based on output quality.

매 retrieval method

• Dense (embedding): 매 semantic similarity.
• BM25 / TF-IDF: 매 keyword.
• Hybrid: 매 둘 다 의 fuse.
• Cross-encoder rerank: 매 expensive but accurate.

매 응용

1. NER / Classification: 매 task-type-similar example.
2. Code generation: 매 similar API usage.
3. Translation: 매 domain-specific phrase.
4. Reasoning: 매 similar pattern (math).
5. Customer service: 매 similar past issue.
6. Schema-aware Text2SQL: 매 similar query pattern.

매 modern best practice

1. Quality > quantity: 매 3-5 example > 매 50.
2. Diverse: 매 same domain 의 cluster X.
3. Recency: 매 newer pattern.
4. Format consistency: 매 same template.
5. Avoid leakage: 매 test 의 example 의 X.

매 modern AI 의 evolution

• In-Context Learning: 매 GPT-3 의 zero / few-shot 의 emergence.
• Long context: 매 100K+ context 의 의 매 100s example.
• Many-shot ICL: 매 1000+ example (Anthropic 2024).
• Adaptive ICL: 매 매 query 의 optimal length.

💻 패턴

Basic dynamic few-shot (LangChain)

from langchain.vectorstores import Chroma
from langchain.embeddings import OpenAIEmbeddings
from langchain.prompts import FewShotPromptTemplate, PromptTemplate

# 매 example pool
examples = [
    {'question': '...', 'answer': '...'},
    # ... 100+ examples
]

# 매 vector store
vectordb = Chroma.from_texts(
    [f"{e['question']} {e['answer']}" for e in examples],
    embedding=OpenAIEmbeddings(),
    metadatas=examples,
)

def dynamic_prompt(query, k=3):
    relevant = vectordb.similarity_search(query, k=k)
    selected = [doc.metadata for doc in relevant]
    
    example_prompt = PromptTemplate(
        input_variables=['question', 'answer'],
        template='Q: {question}\nA: {answer}',
    )
    
    fp = FewShotPromptTemplate(
        examples=selected,
        example_prompt=example_prompt,
        prefix='Answer following the format below.\n\n',
        suffix='\n\nQ: {input}\nA:',
        input_variables=['input'],
    )
    return fp.format(input=query)

MMR (diversity)

def mmr_select(query_emb, candidates, lambda_=0.7, k=5):
    """매 Maximal Marginal Relevance — 매 relevance + 매 diversity."""
    selected = []
    selected_embs = []
    
    while candidates and len(selected) < k:
        scores = []
        for c in candidates:
            relevance = cosine(query_emb, c['emb'])
            if not selected_embs:
                novelty = 0
            else:
                max_sim = max(cosine(c['emb'], se) for se in selected_embs)
                novelty = max_sim
            mmr = lambda_ * relevance - (1 - lambda_) * novelty
            scores.append(mmr)
        
        best_idx = scores.index(max(scores))
        selected.append(candidates[best_idx])
        selected_embs.append(candidates[best_idx]['emb'])
        candidates = [c for i, c in enumerate(candidates) if i != best_idx]
    
    return selected

LLM-as-judge selection

def llm_judge_select(query, candidates, k=5):
    """매 first retrieve large pool → 매 LLM 의 best."""
    # 매 1. retrieve top 20
    pool = vectordb.similarity_search(query, k=20)
    
    # 매 2. LLM 의 select best 5
    formatted = '\n\n'.join(f'[{i}] {p}' for i, p in enumerate(pool))
    prompt = f"""Given the query: "{query}"

Select the {k} MOST USEFUL examples for in-context learning.
Consider: relevance, format, diversity, and pedagogical clarity.

Examples:
{formatted}

Reply with ONLY the indices, comma-separated. e.g., 0, 3, 5, 7, 12"""
    
    indices = parse_indices(llm.generate(prompt))
    return [pool[i] for i in indices]

Hybrid search (BM25 + dense)

from rank_bm25 import BM25Okapi
import numpy as np

class HybridRetriever:
    def __init__(self, examples):
        self.examples = examples
        self.bm25 = BM25Okapi([e['text'].split() for e in examples])
        self.embeddings = embed_all([e['text'] for e in examples])
    
    def search(self, query, k=10, alpha=0.5):
        # 매 BM25
        bm25_scores = self.bm25.get_scores(query.split())
        bm25_norm = bm25_scores / (bm25_scores.max() + 1e-6)
        
        # 매 dense
        q_emb = embed(query)
        dense_scores = cosine_similarity([q_emb], self.embeddings)[0]
        
        # 매 fuse
        scores = alpha * dense_scores + (1 - alpha) * bm25_norm
        top_k = scores.argsort()[-k:][::-1]
        return [self.examples[i] for i in top_k]

Cross-encoder rerank

from sentence_transformers import CrossEncoder

reranker = CrossEncoder('cross-encoder/ms-marco-MiniLM-L-6-v2')

def rerank(query, candidates, k=5):
    pairs = [[query, c['text']] for c in candidates]
    scores = reranker.predict(pairs)
    sorted_idx = scores.argsort()[-k:][::-1]
    return [candidates[i] for i in sorted_idx]

Skill-aware few-shot

def skill_aware_few_shot(query):
    skill = classify_skill(query)  # 매 LLM classifier
    
    # 매 매 skill 의 specific pool
    skill_examples = examples_by_skill[skill]
    
    relevant = vector_search(query, skill_examples, k=3)
    return relevant

Token budget management

def fit_in_context(examples, max_tokens=4000, query_tokens=500):
    """매 context window 의 fit."""
    available = max_tokens - query_tokens
    
    selected = []
    used = 0
    for ex in examples:  # 매 already ranked
        ex_tokens = count_tokens(ex)
        if used + ex_tokens > available:
            break
        selected.append(ex)
        used += ex_tokens
    return selected

Long-context many-shot (modern)

def many_shot_icl(query, n_examples=100):
    """매 100+ example 의 long context (Anthropic 2024)."""
    # 매 simple: 매 just retrieve more
    relevant = vectordb.similarity_search(query, k=n_examples)
    
    # 매 quality > quantity rerank
    reranked = rerank(query, relevant, k=n_examples)
    
    return format_many_shot(reranked, query)

Iterative refinement

def iterative_few_shot(query, max_iter=3):
    examples = initial_select(query, k=5)
    
    for i in range(max_iter):
        result = llm.generate(format_prompt(examples, query))
        critique = self_critique(result, query)
        
        if critique.is_satisfactory: return result
        
        # 매 critique 의 use 의 better example 의 retrieve
        examples = retrieve_for_weakness(query, critique, k=5)
    
    return result

Eval (offline)

def eval_few_shot_strategy(strategy, eval_set):
    correct = 0
    for ex in eval_set:
        examples = strategy(ex['query'])  # 매 LEAVE OUT current example
        prompt = format_prompt(examples, ex['query'])
        pred = llm.generate(prompt)
        if pred == ex['answer']: correct += 1
    return correct / len(eval_set)

매 결정 기준

상황	Strategy
Diverse query	Vector + MMR
High accuracy	LLM-as-judge select
Real-time / cost	Vector top-K only
Long context	Many-shot 100+
Skill variety	Classifier + skill-specific
Critical	Hybrid + cross-encoder rerank

기본값: Hybrid retrieve + MMR + token budget. 매 critical = 매 cross-encoder rerank.

🔗 Graph

• 부모: Prompt_Engineering · In-Context-Learning · RAG
• 변형: kNN-Prompting
• 응용: Faiss · BM25
• Adjacent: Transformer_Architecture_and_LLM_Foundations · CLIP · Sentence-Transformers · Best-of-N_Sampling · Be-Detailed

🤖 LLM 활용

언제: 매 in-context learning. 매 RAG-augmented prompt. 매 task-specific accuracy boost. 언제 X: 매 zero-shot capable task. 매 single template task.

❌ 안티패턴

• No diversity: 매 redundant similar example.
• Test data leakage: 매 evaluation 의 inflate.
• Inconsistent format: 매 confuse model.
• Always max examples: 매 token waste.
• Static pool 의 stale: 매 update 의 X.

🧪 검증 / 중복

• Verified (Liu 2022 What Makes Good In-Context Examples, Anthropic many-shot 2024).
• 신뢰도 A.
• Related: Transformer_Architecture_and_LLM_Foundations · Sentence-Transformers · Best-of-N_Sampling · Be-Detailed · ChatGPT_Emoticon_Prompt_Engineering.

🕓 Changelog

날짜	변경
2026-05-08	Phase 1
2026-05-10	Manual cleanup — strategy + 매 LangChain / MMR / LLM-judge / hybrid / many-shot code