REVIEW 9 cited by
Unlocking Context Constraints of LLMs: Enhancing Context Efficiency of LLMs with Self-Information-Based Content Filtering
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
Signed reviews
read the original abstract
Large language models (LLMs) have received significant attention by achieving remarkable performance across various tasks. However, their fixed context length poses challenges when processing long documents or maintaining extended conversations. This paper proposes a method called \textit{Selective Context} that employs self-information to filter out less informative content, thereby enhancing the efficiency of the fixed context length. We demonstrate the effectiveness of our approach on tasks of summarisation and question answering across different data sources, including academic papers, news articles, and conversation transcripts.
Forward citations
Cited by 9 Pith papers
-
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.
-
Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories
Sleep-time Knowledge Seeding plus Dreaming lets LLMs expand capacity, distill fragile in-context memories into stable parameters, and self-improve without human labels.
-
LoRA-Gen: Specializing Large Language Model via Online LoRA Generation
LoRA-Gen generates task-specific LoRA weights with a cloud-side LLM and reparameterizes them into a smaller edge model, enabling training-free specialization with compressed context.
-
Cartridges: Lightweight and general-purpose long context representations via self-study
A per-corpus trained KV cache, called a Cartridge, matches full-context in-context learning quality on long-document benchmarks while using up to 38.6x less serving memory.
-
Rank It, Then Ask It: Input Reranking for Maximizing the Performance of LLMs on Symmetric Tasks
Reranking symmetric-task inputs so that query-relevant elements occupy high-exposure positions can substantially reduce LLM errors on aggregate queries.
-
Not Worth Another Token: Marginal Value Estimation for Efficient Deep Research Agents
Stage placement, not the scoring rule, dominates pruning effectiveness in deep research agents; early post-retrieval pruning cuts token usage by up to 73% with modest quality loss.
-
AI Governance through Markets
Market governance mechanisms, supported by standardized AI disclosures, can create financial incentives for responsible AI development, according to this policy paper.
-
PIS: Linking Importance Sampling and Attention Mechanisms for Efficient Prompt Compression
PIS prunes tokens with BERT attention and TF-IDF, chooses per-sentence compression ratios with a DDQN, and drops similar sentences via a Russian roulette rule, reporting modest QA and summarization gains on GPT-4o-mini.
-
Legal Document Summarization: Enhancing Judicial Efficiency through Automation Detection
A legal document summarization framework is described, but the experiments use four non-legal summarization datasets and generic equations, so the claimed judicial efficiency improvements are not established.
Discussion (0). Continue with ORCID to comment.