6 papers
ReFreeKV: Towards Threshold-Free KV Cache Compression
Xuanfan Ni, Liyan Xu, Chenyang Lyu +6
To reduce memory consumption during LLM inference, a handful of methods have been proposed for KV cache pruning. While these techniques can accomplish lossless memory reduction on…
How Far Ahead Do LLMs Plan? Uncovering the Latent Horizon in Chain-of-Thought Reasoning
Liyan Xu, Mo Yu, Fandong Meng +1
Chain-of-thought (CoT) reasoning has become a central mechanism for eliciting multi-step reasoning in Large Language Models (LLMs). Yet recent evidence presents a tension: hidden s…
SitEmb-v1.5: Improved Context-Aware Dense Retrieval for Semantic Association and Long Story Comprehension
Junjie Wu, Jiangnan Li, Yuqing Li +6
Retrieval-augmented generation (RAG) over long documents typically involves splitting the text into smaller chunks, which serve as the basic units for retrieval. However, due to de…
ComoRAG: A Cognitive-Inspired Memory-Organized RAG for Stateful Long Narrative Reasoning
Juyuan Wang, Rongchen Zhao, Wei Wei +5
Narrative comprehension on long stories and novels has been a challenging domain attributed to their intricate plotlines and entangled, often evolving relations among characters an…
Dense Retrievers Can Fail on Simple Queries: Revealing The Granularity Dilemma of Embeddings
Liyan Xu, Zhenlin Su, Mo Yu +3
This work stems from an observed limitation of text encoders: embeddings may not be able to recognize fine-grained entities or events within encoded semantics, resulting in failed…
PRELUDE: A Benchmark Designed to Require Global Comprehension and Reasoning over Long Contexts
Mo Yu, Tsz Ting Chung, Chulun Zhou +8
We introduce PRELUDE, a benchmark for evaluating long-context understanding through the task of determining whether a character's prequel story is consistent with the canonical nar…