LANTERN: Layered Archival and Temporal Episodic Retrieval Network for Long-Context LLM Conversations

• URL: http://arxiv.org/abs/2606.05182v1
• Date: Sat, 18 Apr 2026 23:26:48 GMT
• Title: LANTERN: Layered Archival and Temporal Episodic Retrieval Network for Long-Context LLM Conversations
• Abstract summary: Large language models discard critical details when conversation history is compacted to fit within context windows.<n>We present LANTERN, a memory layer that archives every conversation turn and restores relevant details after compaction.<n>On 94 real multi-turn conversations, LANTERN-Rerank recovers 78.3% of verifiable facts lost to compaction.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models discard critical details when conversation history is compacted to fit within finite context windows. We present LANTERN (Layered Archival aNd Temporal Episodic Retrieval Network), a lightweight memory layer that proactively archives every conversation turn and restores relevant details after compaction via hybrid retrieval -- requiring zero LLM calls and adding fewer than 25ms of latency per turn. On 94 real multi-turn conversations (1,894 ground-truth facts, human-validated at kappa=0.81), LANTERN-Rerank recovers 78.3% of verifiable facts lost to compaction, significantly outperforming a faithful reimplementation of MemGPT's LLM-driven extraction and multi-query search pipeline (72.4%; Wilcoxon p<0.0001, 95% CI [+3.1, +8.6] pp, d=0.43) at a fraction of the inference cost. Even without the reranker, base LANTERN matches or exceeds this LLM-driven baseline (p=0.005) using zero LLM calls. When four production LLMs answer fact-bearing questions using LANTERN-restored context, accuracy improves by 8.4 percentage points on average (Wilcoxon p<0.05 for each model individually), demonstrating that the recovered context is useful across diverse model architectures. We release the full evaluation framework -- paired significance tests, failure analysis, fact-type stratification, and compaction robustness analysis -- to support reproducibility and future work.

Related papers

• Grounded Continuation: A Linear-Time Runtime Verifier for LLM Conversations [15.537674351419234]
  Context-manipulation attacks against deployed agents now actively exploit this gap.<n>We close it with a runtime verifier that maintains an explicit dependency graph.<n>Checking whether a continuation is supported reduces to a graph walk; retraction propagates through the same graph to flag exactly the conclusions that lose support.
  arXiv  Detail & Related papers  (2026-05-13T22:54:16Z)
• ReaComp: Compiling LLM Reasoning into Symbolic Solvers for Efficient Program Synthesis [5.1817559908145565]
  LLMs can solve program synthesis tasks but remain inefficient and unreliable on hard instances requiring large search.<n>We use coding agents to compile reasoning traces into reusable symbolic program synthesizers over constrained DSLs.<n>The resulting solvers require no LLM calls at test time and are strong standalone systems.
  arXiv  Detail & Related papers  (2026-05-06T22:08:17Z)
• Resource-Efficient Iterative LLM-Based NAS with Feedback Memory [49.44875022114861]
  Neural Architecture Search (NAS) automates network design, but conventional methods demand substantial computational resources.<n>We propose a closed-loop pipeline leveraging large language models (LLMs) to iteratively generate, evaluate, and refine convolutional neural network architectures.
  arXiv  Detail & Related papers  (2026-03-12T16:00:22Z)
• Grounding by Trying: LLMs with Reinforcement Learning-Enhanced Retrieval [55.63711219190506]
  Large language models (LLMs) often struggle with posing the right search queries. We introduce $underlineLe$arning to $underlineRe$trieve by $underlineT$rying (LeReT) LeReT can improve the absolute retrieval accuracy by up to 29% and the downstream generator evaluations by 17%.
  arXiv  Detail & Related papers  (2024-10-30T17:02:54Z)
• WikiContradict: A Benchmark for Evaluating LLMs on Real-World Knowledge Conflicts from Wikipedia [59.96425443250666]
  Retrieval-augmented generation (RAG) has emerged as a promising solution to mitigate the limitations of large language models (LLMs) In this work, we conduct a comprehensive evaluation of LLM-generated answers to questions based on contradictory passages from Wikipedia. We benchmark a diverse range of both closed and open-source LLMs under different QA scenarios, including RAG with a single passage, and RAG with 2 contradictory passages.
  arXiv  Detail & Related papers  (2024-06-19T20:13:42Z)
• DefAn: Definitive Answer Dataset for LLMs Hallucination Evaluation [39.857198257988685]
  Large Language Models (LLMs) have demonstrated remarkable capabilities, revolutionizing the integration of AI in daily life applications. They are prone to hallucinations, generating claims that contradict established facts, and producing inconsistent responses when the same prompt is presented multiple times. This paper introduces a comprehensive benchmark dataset comprising over 75,000 prompts across eight domains.
  arXiv  Detail & Related papers  (2024-06-13T14:18:13Z)
• Revisiting Large Language Models as Zero-shot Relation Extractors [8.953462875381888]
  Relation extraction (RE) consistently involves a certain degree of labeled or unlabeled data even if under zero-shot setting. Recent studies have shown that large language models (LLMs) transfer well to new tasks out-of-the-box simply given a natural language prompt. This work focuses on the study of exploring LLMs as zero-shot relation extractors.
  arXiv  Detail & Related papers  (2023-10-08T06:17:39Z)
• BooookScore: A systematic exploration of book-length summarization in the era of LLMs [53.42917858142565]
  We develop an automatic metric, BooookScore, that measures the proportion of sentences in a summary that do not contain any of the identified error types. We find that closed-source LLMs such as GPT-4 and 2 produce summaries with higher BooookScore than those generated by open-source models.
  arXiv  Detail & Related papers  (2023-10-01T20:46:44Z)
• LLMs as Factual Reasoners: Insights from Existing Benchmarks and Beyond [135.8013388183257]
  We propose a new protocol for inconsistency detection benchmark creation and implement it in a 10-domain benchmark called SummEdits. Most LLMs struggle on SummEdits, with performance close to random chance. The best-performing model, GPT-4, is still 8% below estimated human performance.
  arXiv  Detail & Related papers  (2023-05-23T21:50:06Z)
• Statistical Knowledge Assessment for Large Language Models [79.07989821512128]
  Given varying prompts regarding a factoid question, can a large language model (LLM) reliably generate factually correct answers? We propose KaRR, a statistical approach to assess factual knowledge for LLMs. Our results reveal that the knowledge in LLMs with the same backbone architecture adheres to the scaling law, while tuning on instruction-following data sometimes compromises the model's capability to generate factually correct text reliably.
  arXiv  Detail & Related papers  (2023-05-17T18:54:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.