165 citations · 400 across the 59 of their papers we have counts for
50 papers · 1 filter
InsightEmb: Learning Action-Intent Embeddings for Agentic Insight Retrieval
Tsz Ting Chung, Jiangnan Li, Jie Zhou +1
Self-improving agents accumulate reusable insights from prior trajectories, making retrieval increasingly important for turning accumulated experience into actionable guidance. At…
A New Role for Relevance: Guiding Corpus Interaction in Agentic Search
Jiangnan Li, Yuqing Li, Mo Yu +2
Relevance is a query-dependent estimate of whether a document or excerpt contains useful evidence. Existing retrieval agents use relevance to select top- content, but document r…
LongNovel: A Multi-Scale Benchmark for Hallucination Detection in Long-Context Novel Summarization
Ruizhi Zhang, Jinwei Chen, Xiangju Lu +4
Although context windows have expanded significantly in recent years, hallucinations in long-context summarization remain a challenge. Long novels are better suited than news or pa…
Many-Shot CoT-ICL: Making In-Context Learning Truly Learn
Tsz Ting Chung, Lemao Liu, Mo Yu +1
While many-shot ICL achieves remarkable performance, prior studies of its scaling behavior have mainly focused on non-reasoning tasks. In this work, we study many-shot ICL on reaso…
MiA-Signature: Approximating Global Activation for Long-Context Understanding
Yuqing Li, Jiangnan Li, Mo Yu +3
A growing body of work in cognitive science suggests that reportable conscious access is associated with \emph{global ignition} over distributed memory systems, while such activati…
Judge Like Human Examiners: A Weighted Importance Multi-Point Evaluation Framework for Generative Tasks with Long-form Answers
Guoxin Yu, Chulun Zhou, Lemao Liu +7
Evaluating the quality of model responses remains challenging in generative tasks with long-form answers, as the expected answers usually contain multiple semantically distinct yet…
Query-focused and Memory-aware Reranker for Long Context Processing
Yuqing Li, Jiangnan Li, Mo Yu +5
Built upon the existing analysis of retrieval heads in large language models, we propose an alternative reranking framework that trains models to estimate passage-query relevance u…
HGMEM: Hypergraph-based Working Memory to Improve Multi-step RAG for Long-Context Complex Relational Modeling
Chulun Zhou, Chunkang Zhang, Guoxin Yu +4
Multi-step retrieval-augmented generation (RAG) has become a widely adopted strategy for enhancing large language models (LLMs) on tasks that demand global comprehension and intens…
Mindscape-Aware Retrieval Augmented Generation for Improved Long Context Understanding
Yuqing Li, Jiangnan Li, Zheng Lin +5
Humans understand long and complex texts by relying on a holistic semantic representation of the content. This global view helps organize prior knowledge, interpret new information…
DivLogicEval: A Framework for Benchmarking Logical Reasoning Evaluation in Large Language Models
Tsz Ting Chung, Lemao Liu, Mo Yu +1
Logic reasoning in natural language has been recognized as an important measure of human intelligence for Large Language Models (LLMs). Popular benchmarks may entangle multiple rea…
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…
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…
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…
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…
The Stochastic Parrot on LLM's Shoulder: A Summative Assessment of Physical Concept Understanding
Mo Yu, Lemao Liu, Junjie Wu +5
In a systematic way, we investigate a widely asked question: Do LLMs really understand what they say?, which relates to the more familiar term Stochastic Parrot. To this end, we pr…
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…
The Essence of Contextual Understanding in Theory of Mind: A Study on Question Answering with Story Characters
Chulun Zhou, Qiujing Wang, Mo Yu +7
Theory-of-Mind (ToM) is a fundamental psychological capability that allows humans to understand and interpret the mental states of others. Humans infer others' thoughts by integrat…
Large Language Models Can Self-Improve in Long-context Reasoning
Siheng Li, Cheng Yang, Zesen Cheng +4
Large language models (LLMs) have achieved substantial progress in processing long contexts but still struggle with long-context reasoning. Existing approaches typically involve fi…
On the token distance modeling ability of higher RoPE attention dimension
Xiangyu Hong, Che Jiang, Biqing Qi +4
Length extrapolation algorithms based on Rotary position embedding (RoPE) have shown promising results in extending the context length of language models. However, understanding ho…
A Survey on the Honesty of Large Language Models
Siheng Li, Cheng Yang, Taiqiang Wu +12
Honesty is a fundamental principle for aligning large language models (LLMs) with human values, requiring these models to recognize what they know and don't know and be able to fai…
An Energy-based Model for Word-level AutoCompletion in Computer-aided Translation
Cheng Yang, Guoping Huang, Mo Yu +6
Word-level AutoCompletion(WLAC) is a rewarding yet challenging task in Computer-aided Translation. Existing work addresses this task through a classification model based on a neura…
Think out Loud: Emotion Deducing Explanation in Dialogues
Jiangnan Li, Zheng Lin, Lanrui Wang +6
Humans convey emotions through daily dialogues, making emotion understanding a crucial step of affective intelligence. To understand emotions in dialogues, machines are asked to re…
On Large Language Models' Hallucination with Regard to Known Facts
Che Jiang, Biqing Qi, Xiangyu Hong +6
Large language models are successful in answering factoid questions but are also prone to hallucination. We investigate the phenomenon of LLMs possessing correct answer knowledge y…
MANGO: A Benchmark for Evaluating Mapping and Navigation Abilities of Large Language Models
Peng Ding, Jiading Fang, Peng Li +6
Large language models such as ChatGPT and GPT-4 have recently achieved astonishing performance on a variety of natural language processing tasks. In this paper, we propose MANGO, a…