Pith. sign in

REVIEW 3 cited by

Compress to Impress: Unleashing the Potential of Compressive Memory in Real-World Long-Term Conversations

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2402.11975 v2 pith:VFI2KOWM submitted 2024-02-19 cs.CL

Compress to Impress: Unleashing the Potential of Compressive Memory in Real-World Long-Term Conversations

classification cs.CL
keywords memorycomedycompressiveconversationsframeworkgenerationinteractionslong-term
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Existing retrieval-based methods have made significant strides in maintaining long-term conversations. However, these approaches face challenges in memory database management and accurate memory retrieval, hindering their efficacy in dynamic, real-world interactions. This study introduces a novel framework, COmpressive Memory-Enhanced Dialogue sYstems (COMEDY), which eschews traditional retrieval modules and memory databases. Instead, COMEDY adopts a "One-for-All" approach, utilizing a single language model to manage memory generation, compression, and response generation. Central to this framework is the concept of compressive memory, which intergrates session-specific summaries, user-bot dynamics, and past events into a concise memory format. To support COMEDY, we curated a large-scale Chinese instruction-tuning dataset, Dolphin, derived from real user-chatbot interactions. Comparative evaluations demonstrate COMEDY's superiority over traditional retrieval-based methods in producing more nuanced and human-like conversational experiences. Our codes are available at https://github.com/nuochenpku/COMEDY.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. SOMA: Efficient Multi-turn LLM Serving via Small Language Model

    cs.CL 2026-05 unverdicted novelty 6.0

    SOMA estimates a local response manifold from early turns and adapts a small surrogate model via divergence-maximizing prompts and localized LoRA fine-tuning for efficient multi-turn serving.

  2. MemRouter: Memory-as-Embedding Routing for Long-Term Conversational Agents

    cs.CL 2026-05 unverdicted novelty 6.0

    A lightweight supervised router using frozen-LLM embeddings for memory admission decisions outperforms LLM-based memory managers in both F1 score and latency on the LoCoMo benchmark.

  3. From Human Memory to AI Memory: A Survey on Memory Mechanisms in the Era of LLMs

    cs.IR 2025-04 unverdicted novelty 5.0

    The paper surveys human memory categories, maps them to LLM memory, and proposes a new three-dimension (object, form, time) categorization into eight quadrants to organize existing work and highlight open problems.