Related papers: Diagnosing Retrieval Bias Under Multiple In-Contex…
Evaluating large language models (LLMs) today rests on fixed benchmarks that apply the same set of items to any model, producing ceiling and floor effects that mask capability gaps. We argue that the most informative evaluation signal lies…
Multimodal Large Language Models (MLLMs) have shown strong performance in multi-image cross-modal retrieval, yet suffer from severe position bias, where predictions are dominated by input order rather than semantic relevance. Through…
Cognitive distortions have been closely linked to mental health disorders, yet their automatic detection remains challenging due to contextual ambiguity, co-occurrence, and semantic overlap. We propose a novel framework that combines Large…
In-context learning (ICL) allows large models to adapt to tasks using a few examples, yet its extension to vision-language models (VLMs) remains fragile. Our analysis reveals that the fundamental limitation lies in an inductive gap, models…
Vision-Language Models (VLMs) are trained on data snapshots of documents, including images and texts. Their training data and evaluation benchmarks are typically static, implicitly treating factual knowledge as time-invariant. However,…
Retrieval-augmented generation (RAG) frameworks enable large language models (LLMs) to retrieve relevant information from a knowledge base and incorporate it into the context for generating responses. This mitigates hallucinations and…
Position bias is a critical problem in information retrieval when dealing with implicit yet biased user feedback data. Unbiased ranking methods typically rely on causality models and debias the user feedback through inverse propensity…
The ability of Large Language Models (LLMs) to extract context from natural language problem descriptions naturally raises questions about their suitability in autonomous decision-making settings. This paper studies the behaviour of these…
The rapid evolution of software libraries creates a significant challenge for Large Language Models (LLMs), whose static parametric knowledge often becomes stale post-training. While retrieval-augmented generation (RAG) is commonly used to…
Large language models accumulate extensive parametric knowledge through pre-training. However, knowledge conflicts occur when outdated or incorrect parametric knowledge conflicts with external knowledge in the context. Existing methods…
Extending the context window of large language models (LLMs) is getting popular recently, while the solution of augmenting LLMs with retrieval has existed for years. The natural questions are: i) Retrieval-augmentation versus long context…
Large Language Models (LLMs) often struggle to maintain their original performance when faced with semantically coherent but task-irrelevant contextual information. Although prior studies have explored this issue using fixed-template or…
Large Vision-Language Models (LVLMs) increasingly rely on retrieval to answer knowledge-intensive multimodal questions. Existing benchmarks overlook conflicts between visual and textual evidence and the importance of generating deflections…
Agentic Retrieval Augmented Generation (RAG) and 'deep research' systems aim to enable autonomous search processes where Large Language Models (LLMs) iteratively refine outputs. However, applying these systems to domain-specific…
The visual world around us constantly evolves, from real-time news and social media trends to global infrastructure changes visible through satellite imagery and augmented reality enhancements. However, Multimodal Large Language Models…
Although large language models (LLMs) are impressive in solving various tasks, they can quickly be outdated after deployment. Maintaining their up-to-date status is a pressing concern in the current era. This paper provides a comprehensive…
Effective incident response (IR) is critical for mitigating cyber threats, yet security teams are overwhelmed by alert fatigue, high false-positive rates, and the vast volume of unstructured Cyber Threat Intelligence (CTI) documents. While…
While large language models (LLMs) leverage both knowledge and reasoning during inference, the capacity to distinguish between them plays a pivotal role in model analysis, interpretability, and development. Inspired by dual-system cognitive…
Retrieval-Augmented Generation (RAG) has become an essential approach for extending the reasoning and knowledge capacity of large language models (LLMs). While prior research has primarily focused on retrieval quality and prompting…
In this paper, we investigate whether Large Language Models (LLMs) actively recall or retrieve their internal repositories of factual knowledge when faced with reasoning tasks. Through an analysis of LLMs' internal factual recall at each…