# FinLifeBench: Exhaustive Life-Event History and Financial-State Reconstruction from Longitudinal Banking Dialogue

arXiv: https://arxiv.org/abs/2609.01198 · HTML: https://mlsanity.com/paper/2609.01198/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 36 references that are in the map.
- First posted on arXiv 1 Sep 2026.

## Builds on (most cited first, 26 of 26)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [RULER: What's the Real Context Size of Your Long-Context Language Models?](https://mlsanity.com/paper/2404.06654/) (2024)
- [Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory](https://mlsanity.com/paper/2504.19413/) (2025)
- [MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling](https://mlsanity.com/paper/1810.00278/) (2018)
- [LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory](https://mlsanity.com/paper/2410.10813/) (2024)
- [FinQA: A Dataset of Numerical Reasoning over Financial Data](https://mlsanity.com/paper/2109.00122/) (2021)
- [Efficient Intent Detection with Dual Sentence Encoders](https://mlsanity.com/paper/2003.04807/) (2020)
- [TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance](https://mlsanity.com/paper/2105.07624/) (2021)
- [Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions](https://mlsanity.com/paper/2507.05257/) (2025)
- [ConvFinQA: Exploring the Chain of Numerical Reasoning in Conversational Finance Question Answering](https://mlsanity.com/paper/2210.03849/) (2022)
- [Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scale](https://mlsanity.com/paper/2504.14225/) (2025)
- [Keep Me Updated! Memory Management in Long-term Conversations](https://mlsanity.com/paper/2210.08750/) (2022)
- [Towards Lifelong Dialogue Agents via Timeline-based Memory Management](https://mlsanity.com/paper/2406.10996/) (2024)
- [From Recall to Forgetting: Benchmarking Long-Term Memory for Personalized Agents](https://mlsanity.com/paper/2604.20006/) (2026)
- [AMemGym: Interactive Memory Benchmarking for Assistants in Long-Horizon Conversations](https://mlsanity.com/paper/2603.01966/) (2026)
- [Getting To Know You: User Attribute Extraction from Dialogues](https://mlsanity.com/paper/1908.04621/) (2019)
- [Locomo-Plus: Beyond-Factual Cognitive Memory Evaluation Framework for LLM Agents](https://mlsanity.com/paper/2602.10715/) (2026)
- [MemConflict: Evaluating Long-Term Memory Systems Under Memory Conflicts](https://mlsanity.com/paper/2605.20926/) (2026)
- [ES-MemEval: Benchmarking Conversational Agents on Personalized Long-Term Emotional Support](https://mlsanity.com/paper/2602.01885/) (2026)
- [MemOps: Benchmarking Lifecycle Memory Operations in Long-Horizon Conversations](https://mlsanity.com/paper/2607.12893/) (2026)
- [CloneMem: Benchmarking Long-Term Memory for AI Clones](https://mlsanity.com/paper/2601.07023/) (2026)
- [MemAudit: Auditing Long-Term Agent Memory via Hidden User-State Recovery](https://mlsanity.com/paper/2606.24595/) (2026)
- [Comprehensive Framework for Evaluating Conversational AI Chatbots](https://mlsanity.com/paper/2502.06105/) (2025)
- [Banking Done Right: Redefining Retail Banking with Language-Centric AI](https://mlsanity.com/paper/2510.07645/) (2025)

## Abstract (arXiv)

Repeated banking interactions require assistants to maintain complete, current, and traceable customer records as life changes emerge incidentally in routine requests. Existing benchmarks emphasize question answering, bounded episodes, or targeted recall rather than exhaustive longitudinal reconstruction. We introduce FinLifeBench, which evaluates two tasks over the same cumulative dialogue: reconstructing every life-event instance with its first-establishing session and reconstructing a complete 34-path financial state at consecutive checkpoints. The benchmark contains 6,000 eight-turn Korean banking sessions from 20 independent synthetic trajectories, with deterministic, exhaustive gold for 24 event types and 34 state paths and consensus quality assurance. Across eleven LLMs under a full-context condition, event-anchor recall falls from 0.591 at 15 sessions to 0.445 at 300. Errors are driven primarily by omitted events rather than poor anchor localization, while financial-state reconstruction frequently treats superseded or potentially outdated information as current; the best GCA@15 reaches 0.470. Performance on the two reconstruction tasks is only weakly associated. These results show that models can localize evidence for recovered events while still failing to maintain complete and temporally valid longitudinal records.