Challenge: Efficient long-context processing remains a challenge for large language models (LLMs) however, the limits of compressibility remain underexplored.
Approach: They propose a method to characterize and detect token overflow in xRAG soft-compression by mapping long contexts into dense vectors that can be directly consumed by the model.
Outcome: The proposed method identifies token overflow with query-agnostic saturation statistics but lacks the capability to detect it.

Similar Papers

A Silver Bullet or a Compromise for Full Attention? A Comprehensive Study of Gist Token-based Context Compression (2025.acl-long)

Copied to clipboard

Challenge: gist-based context compression methods can achieve only slight performance loss on tasks like retrieval-augmented generation and long-document QA, but it faces challenges in tasks like synthetic recall.
Approach: They propose two strategies to improve gist-based context compression in large language models.
Outcome: The proposed methods can achieve only slight performance loss on retrieval-augmented generation and long-document QA tasks, but they face challenges in tasks like synthetic recall.
CacheNotes: Task-Aware Key-Value Cache Compression for Reasoning-Intensive Knowledge Tasks (2026.eacl-long)

Copied to clipboard

Challenge: Current methods for integrating external knowledge into Large Language Models (LLMs) face limitations with broad, multi-source queries, while long-context models are computationally prohibitive.
Approach: They propose a task-aware key-value cache compression method that generates a sequence of CPTs from a corpus and guides a one-time compression of the corpus into a compact, reusable KV cache.
Outcome: The proposed method outperforms Retrieval-Augmented Generation (RAG) on Question-Answering tasks and reduces latency by over 4.
Context Compression for Auto-regressive Transformers with Sentinel Tokens (2023.emnlp-main)

Copied to clipboard

Challenge: Existing Transformer-based LLMs have limited performance due to complexity of attention module . key-value cache is the major memory footprint and inference latency problem .
Approach: They propose a plug-and-play approach that incrementally compresses token activation into compact ones . they also profile the benefit of context compression on improving the system throughout .
Outcome: The proposed approach reduces memory footprint and inference latency by compressing tokens into compact ones.
CompAct: Compressing Retrieved Documents Actively for Question Answering (2024.emnlp-main)

Copied to clipboard

Challenge: Existing methods to condense extensive documents with no loss of information are difficult to implement in real-world scenarios.
Approach: They propose a framework that employs an active strategy to condense extensive documents without losing key information.
Outcome: The proposed framework improves performance and compression rate on multi-hop question-answering benchmarks.
DAST: Context-Aware Compression in LLMs via Dynamic Allocation of Soft Tokens (2025.findings-acl)

Copied to clipboard

Challenge: Existing semantic vector-based compression methods do not account for the intrinsic information density variations between context chunks, instead allocating soft tokens uniformly across context chunk.
Approach: They propose a method that leverages the LLM's intrinsic understanding of contextual relevance to guide compression.
Outcome: The proposed method surpasses state-of-the-art methods on long context tasks.
Refiner: Restructure Retrieved Content Efficiently to Advance Question-Answering Capabilities (2024.findings-emnlp)

Copied to clipboard

Challenge: Large Language Models (LLMs) are limited by their parametric knowledge, leading to hallucinations in knowledge-extensive tasks.
Approach: They propose an end-to-end extract-and-restructure paradigm that leverages a single decoder-only LLM to adaptively extract query-relevant contents verbatim along with the necessary context.
Outcome: Experiments show that a trained Refiner outperforms state-of-the-art RAG and compressing approaches in multiple tasks.
Perception Compressor: A Training-Free Prompt Compression Framework in Long Context Scenarios (2025.findings-naacl)

Copied to clipboard

Challenge: Long prompts contain redundant information and are sensitive to the position of key information in long context scenarios.
Approach: They propose a training-free prompt compression framework that retains key information at token level while removing distracting tokens.
Outcome: The proposed framework outperforms existing methods on long context benchmarks.
LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models (2023.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) are increasingly lengthy and require longer prompts . this paper presents a coarse-to-fine prompt compression method to reduce cost and increase performance.
Approach: They propose a coarse-to-fine prompt compression method that maintains semantic integrity under high compression ratios and a token-level iterative compression algorithm to better model the interdependence between compressed contents.
Outcome: The proposed method yields state-of-the-art performance and allows for up to 20x compression with little performance loss over four datasets from different scenarios.
TCRA-LLM: Token Compression Retrieval Augmented Large Language Model for Inference Cost Reduction (2023.findings-emnlp)

Copied to clipboard

Challenge: ChatGPT and GPT-4 are commercial large language models (LLMs) however, they may produce vague responses or incorrect answers in certain specialized domains.
Approach: They propose a token compression scheme that uses summarization and semantic compression to reduce the token size of LLMs.
Outcome: The proposed method reduces token size by doing summarization and semantic compression while reducing token size with only 1.6% accuracy drop.
SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compression (2026.acl-long)

Copied to clipboard

Challenge: Retrieval-augmented generation (RAG) extends large language models with external knowledge, but it must balance limited effective context, redundant retrieved evidence, and the loss of fine-grained facts.
Approach: They propose a hybrid RAG framework that uses natural-language snippets and semantic compression vectors to preserve passages in text form and compress remaining evidence into interpretable vectors for iterative evidence reranking.
Outcome: The proposed framework improves answer relevance, answer correctness and semantic similarity across 9 datasets and 5 open-source LLMs.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations