IE-as-Cache framework repurposes information extraction as a dynamic cognitive cache to improve agentic reasoning accuracy in LLMs on challenging benchmarks.
Qmsum: A new benchmark for query-based multi-domain meeting summarization
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 2
dataset 2
citation-polarity summary
representative citing papers
The thesis presents a kernel method for multiaccuracy across overlooked subpopulations, information-theoretic optimal watermarking for LLMs, and a simulator showing LLM agents outperforming humans in supply chains while creating tail risks.
Ada-KV is the first head-wise adaptive KV cache budget allocator for LLMs, using a theoretical loss upper bound to allocate eviction differently per attention head and yielding higher quality than uniform methods on long-context benchmarks.
SnapKV selects clustered important KV positions per attention head from an observation window at the prompt end, yielding 3.6x faster generation and 8.2x better memory efficiency on 16K-token inputs with comparable performance across 16 datasets.
RetNet is a new sequence modeling architecture that delivers parallel training, constant-time inference, and competitive language modeling performance as a potential replacement for Transformers.
E2LLM uses encoder-based soft prompt compression for long contexts to improve LLM reasoning on tasks like summarization and QA while maintaining efficiency.
A survey of RAG paradigms, components, benchmarks, and challenges for improving LLMs on knowledge-intensive tasks.
citing papers explorer
-
IE as Cache: Information Extraction Enhanced Agentic Reasoning
IE-as-Cache framework repurposes information extraction as a dynamic cognitive cache to improve agentic reasoning accuracy in LLMs on challenging benchmarks.
-
Trustworthy AI: Ensuring Reliability and Accountability from Models to Agents
The thesis presents a kernel method for multiaccuracy across overlooked subpopulations, information-theoretic optimal watermarking for LLMs, and a simulator showing LLM agents outperforming humans in supply chains while creating tail risks.
-
Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference
Ada-KV is the first head-wise adaptive KV cache budget allocator for LLMs, using a theoretical loss upper bound to allocate eviction differently per attention head and yielding higher quality than uniform methods on long-context benchmarks.
-
SnapKV: LLM Knows What You are Looking for Before Generation
SnapKV selects clustered important KV positions per attention head from an observation window at the prompt end, yielding 3.6x faster generation and 8.2x better memory efficiency on 16K-token inputs with comparable performance across 16 datasets.
-
Retentive Network: A Successor to Transformer for Large Language Models
RetNet is a new sequence modeling architecture that delivers parallel training, constant-time inference, and competitive language modeling performance as a potential replacement for Transformers.
-
E2LLM: Encoder Elongated Large Language Models for Long-Context Understanding and Reasoning
E2LLM uses encoder-based soft prompt compression for long contexts to improve LLM reasoning on tasks like summarization and QA while maintaining efficiency.
-
Retrieval-Augmented Generation for Large Language Models: A Survey
A survey of RAG paradigms, components, benchmarks, and challenges for improving LLMs on knowledge-intensive tasks.