Related papers: CogCanvas: Verbatim-Grounded Artifact Extraction f…
We propose RecaLLM, a set of reasoning language models post-trained to make effective use of long-context information. In-context retrieval, which identifies relevant evidence from context, and reasoning are deeply intertwined: retrieval…
Recently, large language models (LLMs), such as GPT-4, stand out remarkable conversational abilities, enabling them to engage in dynamic and contextually relevant dialogues across a wide range of topics. However, given a long conversation,…
Key point extraction is an important task in argument summarization which involves extracting high-level short summaries from arguments. Existing approaches for KP extraction have been mostly evaluated on the popular ArgKP21 dataset. In…
Although Large Language Models (LLMs) demonstrate proficiency in knowledge-intensive tasks, current interfaces frequently precipitate cognitive misalignment by failing to externalize users' underlying reasoning structures. Existing tools…
Human communication heavily relies on laconism and inferential pragmatics, allowing listeners to successfully reconstruct rich meaning from sparse, telegraphic speech. In contrast, large language models (LLMs) owe much of their stellar…
Vision-language models (VLMs) rely on long visual token sequences for visual understanding, making the prefill stage expensive in both computation and memory. Most existing pruning methods follow an absolute-ranking paradigm, assigning…
Recent advancements in Large Video-Language Models (LVLMs) have led to promising results in multimodal video understanding. However, it remains unclear whether these models possess the cognitive capabilities required for high-level tasks,…
There has been a growing effort to replace manual extraction of data from research papers with automated data extraction based on natural language processing, language models, and recently, large language models (LLMs). Although these…
Multimodal language models (MLLMs) are increasingly being applied in real-world environments, necessitating their ability to interpret 3D spaces and comprehend temporal dynamics. Current methods often rely on specialized architectural…
Large vision-language models (LVLMs) achieve strong multimodal understanding, but their inference cost grows rapidly with the number of visual tokens, especially for high-resolution images and long videos. Existing attention-based methods…
Incorporating external knowledge in large language models (LLMs) enhances their utility across diverse applications, but existing methods have trade-offs. Retrieval-Augmented Generation (RAG) fetches evidence via similarity search, but key…
Long-term conversational large language model (LLM) agents require memory systems that can recover relevant evidence from historical interactions without overwhelming the answer stage with irrelevant context. However, existing memory…
Large language models (LLMs) are widely deployed with rapidly expanding context windows to support increasingly demanding applications. However, long contexts pose significant deployment challenges, primarily due to the KV cache whose size…
Modern large language models (LLMs) extend context lengths to millions of tokens, enabling coherent, personalized responses grounded in long conversational history. However, the Key-Value (KV) cache grows linearly with the extended dialogue…
Recently an influx of studies claim emergent cognitive abilities in large language models (LLMs). Yet, most rely on anecdotes, overlook contamination of training sets, or lack systematic Evaluation involving multiple tasks, control…
Large Language Models (LLMs) have demonstrated remarkable capabilities in leveraging extensive external knowledge to enhance responses in multi-turn and agentic applications, such as retrieval-augmented generation (RAG). However, processing…
Large language models (LLMs) have shown strong performance in zero-shot summarization, but often struggle to model document structure and identify salient information in long texts. In this work, we introduce StrucSum, a training-free…
Long-term memory is essential for conversational agents to maintain coherence, track persistent tasks, and provide personalized interactions across extended dialogues. However, existing approaches as Retrieval-Augmented Generation (RAG) and…
Long-horizon language agents accumulate conversation history far faster than any fixed context window can hold, making memory management critical to both answer accuracy and serving cost. Existing approaches either expand the context window…
Large language models with long context windows can answer complex questions directly from full-length academic, technical, and policy documents, but passing entire documents is often costly, slow, and can degrade answer quality while…