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

---
id: wiki-2026-0508-dynamic-few-shot
title: Dynamic Few-Shot Selection
category: 10_Wiki/Topics
status: verified
canonical_id: self
aliases: [dynamic few-shot, in-context learning, ICL retrieval, RAG few-shot, kNN-prompting]
duplicate_of: none
source_trust_level: A
confidence_score: 0.9
verification_status: applied
tags: [prompt-engineering, few-shot, in-context-learning, rag, vector-search, llm, retrieval]
raw_sources: []
last_reinforced: 2026-05-10
github_commit: pending
tech_stack:
  language: Python
  framework: 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)
```python
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)
```python
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
```python
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)
```python
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
```python
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
```python
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
```python
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)
```python
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
```python
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)
```python
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|Prompt-Engineering]] · [[In-Context-Learning]] · [[RAG]]
- 변형: [[kNN-Prompting]]
- 응용: [[Faiss]] · [[BM25]]
- Adjacent: [[Transformer_Architecture_and_LLM_Foundations|BERT]] · [[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|BERT]] · [[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 |