Understanding Large Language Models (LLMs) is key to ensure their safe and beneficial deployment. This task is complicated by the difficulty of interpretability of LLM structures, and the inability to have all their outputs human-evaluated. In this paper, we present the first step towards a predictive framework, where the genre of a text used to prompt an LLM, is predicted based on its activations. Using Mistral-7B and two datasets, we show that genre can be extracted with F1-scores of up to 98% and 71% using scikit-learn classifiers. Across both datasets, results consistently outperform the control task, providing a proof of concept that text genres can be inferred from LLMs with shallow learning models.

Narrative comprehension on long stories and novels has been a challenging domain attributed to their intricate plotlines and entangled, often evolving relations among characters and entities. Given the LLM's diminished reasoning over extended context and its high computational cost, retrieval-based approaches remain a pivotal role in practice. However, traditional RAG methods could fall short due to their stateless, single-step retrieval process, which often overlooks the dynamic nature of capturing interconnected relations within long-range context. In this work, we propose ComoRAG, holding the principle that narrative reasoning is not a one-shot process, but a dynamic, evolving interplay between new evidence acquisition and past knowledge consolidation, analogous to human cognition on reasoning with memory-related signals in the brain. Specifically, when encountering a reasoning impasse, ComoRAG undergoes iterative reasoning cycles while interacting with a dynamic memory workspace. In each cycle, it generates probing queries to devise new exploratory paths, then integrates the retrieved evidence of new aspects into a global memory pool, thereby supporting the emergence of a coherent context for the query resolution. Across four challenging long-context narrative benchmarks (200K+ tokens), ComoRAG outperforms strong RAG baselines with consistent relative gains up to 11% compared to the strongest baseline. Further analysis reveals that ComoRAG is particularly advantageous for complex queries requiring global context comprehension, offering a principled, cognitively motivated paradigm towards retrieval-based stateful reasoning. Our framework is made publicly available at https://github.com/EternityJune25/ComoRAG.

Graph-based retrieval-augmented generation (Graph-based RAG) has demonstrated significant potential in enhancing Large Language Models (LLMs) with structured knowledge. However, existing methods face three critical challenges: Inaccurate Graph Construction, caused by LLM hallucination; Poor Reasoning Ability, caused by failing to generate explicit reasons telling LLM why certain chunks were selected; and Inadequate Answering, which only partially answers the query due to the inadequate LLM reasoning, making their performance lag behind NaiveRAG on certain tasks. To address these issues, we propose AGRAG, an advanced graph-based retrieval-augmented generation framework. When constructing the graph, AGRAG substitutes the widely used LLM entity extraction method with a statistics-based method, avoiding hallucination and error propagation. When retrieval, AGRAG formulates the graph reasoning procedure as the Minimum Cost Maximum Influence (MCMI) subgraph generation problem, where we try to include more nodes with high influence score, but with less involving edge cost, to make the generated reasoning paths more comprehensive. We prove this problem to be NP-hard, and propose a greedy algorithm to solve it. The MCMI subgraph generated can serve as explicit reasoning paths to tell LLM why certain chunks were retrieved, thereby making the LLM better focus on the query-related part contents of the chunks, reducing the impact of noise, and improving AGRAG's reasoning ability. Furthermore, compared with the simple tree-structured reasoning paths, our MCMI subgraph can allow more complex graph structures, such as cycles, and improve the comprehensiveness of the generated reasoning paths.

Long context inference scenarios have become increasingly important for large language models, yet they introduce significant computational latency. While prior research has optimized long-sequence inference through operators, model architectures, and system frameworks, tokenization remains an overlooked bottleneck. Existing parallel tokenization methods accelerate processing through text segmentation and multi-process tokenization, but they suffer from inconsistent results due to boundary artifacts that occur after merging. To address this, we propose LoPT, a novel Lossless Parallel Tokenization framework that ensures output identical to standard sequential tokenization. Our approach employs character-position-based matching and dynamic chunk length adjustment to align and merge tokenized segments accurately. Extensive experiments across diverse long-text datasets demonstrate that LoPT achieves significant speedup while guaranteeing lossless tokenization. We also provide theoretical proof of consistency and comprehensive analytical studies to validate the robustness of our method.

Graph-based RAG constructs a knowledge graph (KG) from text chunks to enhance retrieval in Large Language Model (LLM)-based question answering. It is especially beneficial in domains such as biomedicine, law, and political science, where effective retrieval often involves multi-hop reasoning over proprietary documents. However, these methods demand numerous LLM calls to extract entities and relations from text chunks, incurring prohibitive costs at scale. Through a carefully designed ablation study, we observe that certain words (termed concepts) and their associated documents are more important. Based on this insight, we propose Graph-Guided Concept Selection (G2ConS). Its core comprises a chunk selection method and an LLM-independent concept graph. The former selects salient document chunks to reduce KG construction costs; the latter closes knowledge gaps introduced by chunk selection at zero cost. Evaluations on multiple real-world datasets show that G2ConS outperforms all baselines in construction cost, retrieval effectiveness, and answering quality.

Measuring scientific paper innovation is both important and challenging. Existing content-based methods often overlook the full-paper context, fail to capture the full scope of innovation, and lack generalization. We propose HSPIM, a hierarchical and training-free framework based on large language models (LLMs). It introduces a Paper-to-Sections-to-QAs decomposition to assess innovation. We segment the text by section titles and use zero-shot LLM prompting to implement section classification, question-answering (QA) augmentation, and weighted innovation scoring. The generated QA pair focuses on section-level innovation and serves as additional context to improve the LLM scoring. For each chunk, the LLM outputs a novelty score and a confidence score. We use confidence scores as weights to aggregate novelty scores into a paper-level innovation score. To further improve performance, we propose a two-layer question structure consisting of common and section-specific questions, and apply a genetic algorithm to optimize the question-prompt combinations. Furthermore, under the fine-grained structure of innovation, we extend HSPIM to an HSPIM$^+$ that generates novelty, contribution, and feasibility scores with respective confidence scores. Comprehensive experiments on scientific conference paper datasets show that HSPIM outperforms baseline methods in effectiveness, generalization, and interpretability. Demo code is available at https://github.com/Jasaxion/HSPIM.

Retrieval-Augmented Generation (RAG) systems suffer from severe time-to-first-token (TTFT) bottlenecks due to long input sequences. Existing KV cache reuse methods face a fundamental trade-off: prefix caching requires identical prefixes that rarely occur in RAG scenarios, while direct precomputation sacrifices quality due to missing inter-chunk attention and repeated attention sinks. Recent methods like APE and CacheBlend partially address these issues but remain inadequate for robust RAG applications. This paper presents CacheClip, a novel framework that achieves both fast TTFT and high generation quality. Our key insight is that small auxiliary LLMs exhibit similar last-layer attention distributions to primary LLMs (the target model for generation), enabling efficient identification of tokens critical for restoring inter-chunk attention, thereby significantly improving response quality on cross-chunk reasoning tasks. CacheClip integrates three techniques: (1) auxiliary-model-guided token selection for selective KV cache recomputation, where the auxiliary model is finetuned to improve selection accuracy, (2) shared prefixes to eliminate redundant attention sinks, and (3) grouping strategy to maintain local coherence during partial KV cache updates. Experiments show CacheClip retains up to 94.8% and 85.0% of full-attention performance on NIAH and LongBench, outperforming APE and CacheBlend by 25.2% and 35.1% on NIAH (with reomp% = 20%). Meanwhile, CacheClip accelerates LLM inference by up to 1.92x in prefill time, providing a practical solution to the efficiency-quality trade-off in RAG systems.

API calls for each position identified in a piece of text. Question Answering We use the Atlas model of Izacard et al. (2022) finetuned on Natural Questions Calculator Our calculator is based on a simple Python script and only supports the operators " It does not return any result for syntactically invalid equations. "=", "equals", "equal to", "total of", "average of" followed by a number, or (iii) contain at least three English text before generating API calls. Below, we list the prompts used to sample API calls for each tool considered. Your task is to add calls to a Question Answering API to a piece of text. Input: Joe Biden was born in Scranton, Pennsylvania. Output: Joe Biden was born in [QA("Where was Joe Biden born?")] Scranton, [QA("In Output: Coca-Cola, or [QA("What other name is Coca-Cola known by?")] Coke, is Your task is to add calls to a Calculator API to a piece of text.

This study investigates the register variation in texts written by humans and comparable texts produced by large language models (LLMs). Biber's multidimensional analysis (MDA) (Biber, 1988) is applied to a sample of human-written texts and AI-created texts generated to be their counterparts to find the dimensions of variation in which LLMs differ most significantly and most systematically from humans. As textual material, a new LLM-generated corpus AI-Brown is used, which is comparable to BE21 (a Brown family corpus representing contemporary British English). Since all languages except English are underrepresented in the training data of frontier LLMs, similar analysis is replicated on Czech using AI-Koditex corpus and Czech multidimensional model (Cvrˇ cek et al., 2018). Examined were 16 frontier models in various settings and prompts, with emphasis placed on the difference between base models and instruction-tuned models. Based on this, a benchmark is created through which models can be compared with each other and ranked in interpretable dimensions.