REVIEW 8 cited by
CompAct: Compressing Retrieved Documents Actively for Question Answering
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
CompAct: Compressing Retrieved Documents Actively for Question Answering
read the original abstract
Retrieval-augmented generation supports language models to strengthen their factual groundings by providing external contexts. However, language models often face challenges when given extensive information, diminishing their effectiveness in solving questions. Context compression tackles this issue by filtering out irrelevant information, but current methods still struggle in realistic scenarios where crucial information cannot be captured with a single-step approach. To overcome this limitation, we introduce CompAct, a novel framework that employs an active strategy to condense extensive documents without losing key information. Our experiments demonstrate that CompAct brings significant improvements in both performance and compression rate on multi-hop question-answering benchmarks. CompAct flexibly operates as a cost-efficient plug-in module with various off-the-shelf retrievers or readers, achieving exceptionally high compression rates (47x).
Forward citations
Cited by 8 Pith papers
-
Prism-Reranker: Beyond Relevance Scoring -- Jointly Producing Contributions and Evidence for Agentic Retrieval
Prism-Reranker models output relevance, contribution statements, and evidence passages to support agentic retrieval beyond scalar scoring.
-
What to Keep, What to Forget: A Rate--Distortion View of Memory Compaction in LLMs and Agents
KV-cache eviction, prompt compression, recurrent state bounding, and agent memory consolidation are unified as one rate-distortion problem with a shared lower bound, shared failure mode, and transferable mechanisms.
-
End-to-End Context Compression at Scale
LCLMs are scaled 0.6B-encoder 4B-decoder compressors pre-trained on over 350B tokens that improve the Pareto frontier for general-task performance, compression speed, and peak memory in long-context language model inference.
-
Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression
A pipeline combining a question-aware formula-preserving compressor, mixed-ratio SFT, and hierarchical RL compresses CoT on math benchmarks to ~27% of original tokens while preserving or slightly improving accuracy.
-
Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression
Extra-CoT trains a semantic compressor on math CoT data, applies mixed-ratio SFT, and uses CHRPO reinforcement learning to achieve over 73% token reduction on MATH-500 with 0.6% accuracy gain on Qwen3-1.7B.
-
MHA-RAG: Improving Efficiency, Accuracy, and Consistency by Encoding Exemplars as Soft Prompts
MHA-RAG encodes retrieved exemplars into order-invariant soft prompts via multi-head attention, claiming ~20-point effective-accuracy gains over RAG at ~10x lower inference FLOPs.
-
ContextSniper: AntTrail's Token-Efficient Code Memory for Repository-Level Program Repair
A context-access layer for repair agents cuts token use ~39–52% on SWE-bench Lite without a clear drop in submitted resolution rates.
-
ContextSniper: AntTrail's Token-Efficient Code Memory for Repository-Level Program Repair
ContextSniper reduces token use by 38.9-51.5% in repository-level program repair agents on SWE-bench Lite with 2 percentage point drops in resolution rate.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.