Fusion-in-Decoder: How Multi-Passage Retrieval Improves Generative QA
FiD encodes retrieved passages separately and fuses them in the decoder, beating RAG-Sequence by 4–11 points on NQ and TriviaQA, the synthesis ledger QA needs.
#beancount
Beancount
Beancount ledger format, tooling, and ecosystem research
Multiagent LLM Debate: Real Accuracy Gains, Uncontrolled Compute, and Collective Delusion
Multiagent debate gained 14.8 points on arithmetic, but equal-budget single agents match it. That limits debate as a safe check before a ledger commit.
LLMs Are Not Useful for Time Series Forecasting: What NeurIPS 2024 Means for Finance AI
NeurIPS 2024 ablation: dropping the LLM from Time-LLM and CALF improves accuracy, with up to 1,383× faster training. Use purpose-built models for finance AI.
Fine-Tuning vs. RAG: Why Retrieval Wins for Injecting New Knowledge into LLMs
RAG hits 0.875 accuracy on post-cutoff facts while fine-tuning plateaus at 0.504. For agents needing frequent ledger updates, retrieval beats fine-tuning.
IRCoT: Interleaving Retrieval with Chain-of-Thought for Multi-Step QA
IRCoT adds +11.3 recall and +7.1 F1 on HotpotQA over one-step RAG by querying retrieval at every reasoning step. A 3B model can then beat GPT-3 175B.
FLARE: Active Retrieval Augmented Generation
FLARE hits 51.0 EM on 2WikiMultihopQA versus 39.4 for single-retrieval RAG, but calibration failures in chat models limit it for finance agents.
RAG: 44.5 EM on NQ — and why ledger indexes go stale
Lewis et al. hit 44.5 EM on Natural Questions with a frozen FAISS index; for Beancount ledgers that means reindex-or-miss when balances change daily.
FinQA: The Benchmark Measuring AI Numerical Reasoning on Financial Reports
FinQA found neural models scored 61% on financial-report math versus 91% for human experts, collapsing to 22% on three-or-more-step programs.
DSPy: Replacing Brittle Prompt Engineering with Compiled LLM Pipelines
DSPy's compiler lifted Llama2-13b from 9.4% to 46.9% on GSM8K, pointing finance AI pipelines toward maintainable declarative LLM calls.
LATS: Language Agent Tree Search — Reasoning, Acting, and Planning in One Framework
LATS unifies ReAct, Tree of Thoughts, and Reflexion in one MCTS framework, hitting 92.7% pass@1 on HumanEval with GPT-4.
Self-RAG: Adaptive Retrieval and Self-Critique for LLMs
Self-RAG trains an LLM to decide when to retrieve and self-grade results, hitting 55.8% on PopQA and 80.2 FactScore — beating ChatGPT on five benchmarks.
Voyager: skill libraries unlock 3.3× more item discovery
Voyager's persistent code skill library discovers 3.3× more Minecraft items than prior SOTA without fine-tuning—the reuse pattern ledger agents need.