Skip to main content
Beancount.io LogoBeancount.io

85 tagged with "Machine Learning"

Machine learning techniques for financial data analysis and automation

View all tags

LLMs Cannot Self-Correct Reasoning Yet — ICLR 2024 Findings and Finance AI Implications
·mike

LLMs Cannot Self-Correct Reasoning Yet — ICLR 2024 Findings and Finance AI Implications

Huang et al. (ICLR 2024) show that LLMs asked to review their own reasoning without external feedback consistently degrade accuracy — GPT-4 drops from 95.5% to 91.5% on GSM8K — and what this means for designing reliable Beancount journal entry agents.

llm
ai
machine-learning
automation
+3
Tree of Thoughts: Deliberate Problem Solving with LLM Search
·mike

Tree of Thoughts: Deliberate Problem Solving with LLM Search

Tree of Thoughts (ToT) achieves 74% on Game of 24 vs 4% for standard GPT-4 CoT by organizing LLM reasoning into a branching search tree with pruning and backtracking — with direct implications for multi-step financial classification and tax optimization in Beancount workflows.

ai
llm
machine-learning
automation
+2
CRITIC: Why LLM Self-Correction Requires External Tool Feedback
·mike

CRITIC: Why LLM Self-Correction Requires External Tool Feedback

CRITIC (ICLR 2024) achieves 7.7 F1 gains on open-domain QA and a 79.2% toxicity reduction by grounding LLM revision in external tool signals — a verify-then-correct loop that maps directly onto write-back safety for Beancount finance agents.

ai
llm
machine-learning
automation
+4
Reflexion: Language Agents That Learn from Mistakes Without Retraining
·mike

Reflexion: Language Agents That Learn from Mistakes Without Retraining

Reflexion (NeurIPS 2023) lets LLM agents improve by storing verbal post-mortems in an episodic buffer — no weight updates required. It reaches 91% on HumanEval with GPT-4 but fails on WebShop, revealing a structural constraint: verbal reinforcement only works when the evaluator produces a crisp, actionable signal. Here is what that means for building a self-correcting Beancount ledger agent.

ai
llm
machine-learning
automation
+2
Себесъгласуваност: Изборът чрез мнозинство повишава точността на веригата от мисли
·mike

Себесъгласуваност: Изборът чрез мнозинство повишава точността на веригата от мисли

Себесъгласуваността заменя „алчното“ декодиране на веригата от мисли с гласуване с мнозинство върху N извлечени пътища на разсъждение — повишавайки точността на GPT-3 върху GSM8K със 17,9 процентни пункта без допълнително обучение — и се прилага директно към многостъпкови финансови изчисления, където единичното декодиране на модела е ненадеждно.

ai
llm
machine-learning
automation
+3
PAL: Program-Aided Language Models for Reliable Financial Arithmetic
·mike

PAL: Program-Aided Language Models for Reliable Financial Arithmetic

PAL (Program-Aided Language Models) achieves a +38pp accuracy gain over chain-of-thought on arithmetic-heavy tasks by delegating computation to a Python interpreter — a directly applicable architecture for reliable Beancount ledger queries and finance AI.

ai
llm
machine-learning
beancount
+3
Constitutional AI for Accounting Agents: RLAIF, Policy Rules, and Goodharting Risks
·mike

Constitutional AI for Accounting Agents: RLAIF, Policy Rules, and Goodharting Risks

Anthropic's Constitutional AI paper (Bai et al., 2022) trains LLMs to follow rules using AI-generated feedback rather than human harm labels. This research log examines how the RLAIF critique-revise-preference pipeline maps onto write-back safety for autonomous Beancount ledger agents — and what Goodharting, calibration failures, and dual-use risks look like when the "constitution" is a chart of accounts instead of an ethics ruleset.

ai
machine-learning
llm
automation
+3
Chain-of-Thought Prompting: Precision-Recall Trade-offs for Finance AI
·mike

Chain-of-Thought Prompting: Precision-Recall Trade-offs for Finance AI

A close reading of Wei et al.'s 2022 Chain-of-Thought paper and what it means for finance AI — why CoT raises precision but may cut recall on rare-event detection, why the scale threshold matters for production agents, and what a finance team building on LLMs should watch out for.

ai
llm
machine-learning
data-science
+3
PHANTOM (NeurIPS 2025): Measuring LLM Hallucination Detection in Financial Documents
·mike

PHANTOM (NeurIPS 2025): Measuring LLM Hallucination Detection in Financial Documents

PHANTOM (NeurIPS 2025) is the first benchmark to measure LLM hallucination detection on real SEC filings across context lengths up to 30,000 tokens. Qwen3-30B-A3B-Thinking leads with F1=0.882; 7B models score near random guessing — with direct implications for autonomous accounting agents.

llm
ai
machine-learning
finance
+4
FinMaster Benchmark: Why LLMs Score 96% on Financial Literacy but 3% on Statement Generation
·mike

FinMaster Benchmark: Why LLMs Score 96% on Financial Literacy but 3% on Statement Generation

FinMaster (arXiv:2505.13533) benchmarks o3-mini, Claude 3.7 Sonnet, and DeepSeek-V3 across 183 financial tasks—revealing that models score 96% on financial literacy but collapse to 3% on statement generation, with multi-step consulting tasks losing 21 accuracy points from error propagation.

llm
accounting
ai
financial-statements
+3
ReAct: Synergizing Reasoning and Acting in Language Models
·mike

ReAct: Synergizing Reasoning and Acting in Language Models

ReAct (Yao et al., ICLR 2023) interleaves chain-of-thought reasoning with tool actions in a single trajectory, outperforming pure CoT on fact verification and imitation learning on embodied tasks by 34 percentage points. This analysis covers the paper's failure modes — search-induced distraction and compounding errors — and what they mean for autonomous agents writing back to Beancount ledgers.

ai
llm
machine-learning
automation
+3
Toolformer: Self-Supervised Tool Use and Its Limits for Finance AI
·tian

Toolformer: Self-Supervised Tool Use and Its Limits for Finance AI

A close reading of Toolformer (Meta AI, NeurIPS 2023): how perplexity-filtered self-supervised training teaches a 6.7B-parameter model to call external APIs, where it outperforms GPT-3 175B on arithmetic benchmarks, and why its single-step architecture cannot support the chained tool calls required for structured ledger operations.

ai
llm
machine-learning
automation
+4
Showing 73–84 of 85 posts