arXiv AI
Aug 5
Soft Guidance Starts to Outperform CoT Prompting as LLMs Improve
arXiv:2608. 03550v1 Announce Type: new Abstract: Chain-of-Thought (CoT) prompting remains the standard baseline for evaluating models' reasoning abilities.
Large language models
Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
arXiv AI
Aug 5
CURV: Enhancing Chart Understanding Through Curriculum Visual Grounded Reasoning
arXiv:2608. 02833v1 Announce Type: cross Abstract: Chart question answering (CQA) requires multimodal large language models (MLLMs) to integrate visual comprehension with logical reasoning, yet current models struggle with accurate visual grounding and coherent reasoning chains.
arXiv AI
Aug 5
Shorter Reasoning, Earlier Answers? An Evaluation of Reasoning Interfaces
arXiv:2608. 03401v1 Announce Type: cross Abstract: Large language models often reason at length before answering, increasing cost and latency.
arXiv AI
Aug 5
Pattern over Pixels: Measuring Pattern Completion Bias in Multimodal Code Generation
arXiv:2608. 03691v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) are increasingly used to translate webpage screenshots into front-end code, but repeated UI patterns may sway them toward visually incorrect yet pattern-consistent outputs.
arXiv AI
Aug 5
Separating quantum circuits from classical LLMs
arXiv:2608. 03962v1 Announce Type: cross Abstract: Modern large language models - transformers and diffusion language models - are built around two canonical algorithmic tasks: prediction and generation.
arXiv AI
Aug 5
Before Reasoning Can Fail: Pre-Evidence Procedural Failures in Agentic RAG
arXiv:2608. 02011v2 Announce Type: replace Abstract: Agentic retrieval-augmented generation (RAG) systems can fail before evidence-conditioned reasoning is tested: an agent may retrieve candidate snippets but finalize without inspecting them.
arXiv AI
Aug 5
Patient-centered data science: an integrative framework for evaluating and predicting clinical outcomes in the digital health era
arXiv:2408. 02677v2 Announce Type: replace-cross Abstract: This study proposes a novel, integrative framework for patient-centered data science in the digital health era.
arXiv AI
Aug 5
Toward Understanding the Transferability of Adversarial Suffixes in Large Language Models
arXiv:2510. 22014v2 Announce Type: replace-cross Abstract: Discrete optimization-based jailbreaking attacks on large language models aim to generate short, nonsensical suffixes that, when appended onto input prompts, elicit disallowed content.
arXiv AI
Aug 5
$\pi$-Attention: Online Efficient Sparse Transformers for Long-Context Modeling
arXiv:2511. 10696v3 Announce Type: replace-cross Abstract: Sparse attention is crucial in long-context Transformers, which restricts each token to a limited neighborhood and thereby reduces the quadratic cost of full self-attention.
arXiv AI
Aug 5
Improving Reproducibility in Evaluation through Multi-Level Annotator Modeling
arXiv:2605. 13801v2 Announce Type: replace-cross Abstract: As generative AI models such as large language models (LLMs) become more pervasive, ensuring the safety, robustness, and overall trustworthiness of these systems is paramount.
arXiv Machine Learning
Aug 5
Inverted Detection and Control in Steering Vectors
arXiv:2608. 02957v1 Announce Type: new Abstract: Steering vectors (SVs) are widely used to influence the expression of concepts (e.
arXiv AI
Aug 5
GPTKB 2.0: Direct Construction of Disambiguated Knowledge Bases from Large Language Models
arXiv:2608. 03729v1 Announce Type: cross Abstract: Automated Knowledge Base Construction (AKBC) is a core NLP task, and recent work proposes generating knowledge bases directly from large language models (LLMs), treating the model itself as the knowledge source.
arXiv AI
Aug 5
MDLMPE: Distribution Aware Positional Encoding for Masked Diffusion Language Models
arXiv:2608. 03769v1 Announce Type: cross Abstract: Masked diffusion language models (MDLMs) enable parallel generation and bidirectional context modeling, but their positional context differs fundamentally from that of autoregressive (AR) models.
Hugging Face Trending Papers
Aug 5
Social Pressure Breaks Majority Voting in LLM Safety Panels
Large language models (LLMs) are increasingly used to detect unsafe content. A common approach is to combine judgments from a panel of models to correct individual mistakes, but this benefit may disappear when every model sees the same misleading context before voting.
Hugging Face Trending Papers
Aug 5
Training-Free Hashing-Based Attention via Binary Principal Components
Long-context large language models (LLMs) are increasingly deployed in real-world applications, yet self-attention remains a major efficiency bottleneck -- especially during decoding -- due to the necessity of repeatedly processing ever-growing key-value (KV) caches. Existing sparse attention reduce computation by attending to fewer KV pairs, but often suffer from substantial accuracy degradation, require additional training, or rely on expensive hashing.
Hugging Face Trending Papers
Aug 5
EdgeLM: Edge Demonstrations for Language Models' Table Understanding
Large language models (LLMs) perform table-centric prediction through in-context learning, making demonstration selection critical to performance. Existing retrieval methods prioritize similarity to the query, but similar demonstrations often reinforce the model's likely prediction rather than reveal the distinctions needed for difficult decisions.
Hugging Face Trending Papers
Aug 5
HyPASE: Hyperbolic Geometry for Parameter-Efficient Speech Emotion Fine-Tuning Framework for Large Audio-Language Models
Large Audio-Language Models (LALMs) excel at general speech understanding; however, adapting them to fine-grained tasks like Speech Emotion Recognition (SER) remains a significant bottleneck. Current Parameter-Efficient Fine-Tuning (PEFT) methods typically operate in flat Euclidean space, and this geometry fails to capture the multi-granularity nature of emotion cues, which range from low-level prosody to high-level semantics.
Hugging Face Trending Papers
Aug 5
Looking in the Mirror: Introspecting Side-Effect Misalignments Induced by Fine-Tuning
Fine-tuning enables a source model to acquire desired capabilities and behaviors in a target domain while retaining much of its general-purpose competence. However, this adaptation process can also degrade alignment properties that were present in the source model.
Hugging Face Trending Papers
Aug 5
Right Reset: Chunking by Prefix Removal
Removing the left context from a causal language model reveals a useful kind of boundary: an edge where the model processes the same right-hand tokens with little change. We turn this observation into prefix-removal probing and introduce Right Reset (RR), which measures preservation of the right-hand hidden-state trajectory.
Hugging Face Trending Papers
Aug 5
Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic)
Autonomous cyber defense systems based on Deep Reinforcement Learning (DRL) have attracted significant research attention, yet remain evaluated almost exclusively against static, heuristic red agents, leaving their robustness against adaptive threats critically understudied. Meanwhile, recent advances in Reinforcement Learning with Verifiable Rewards (RLVR) have improved LLM reasoning, but their integration into cybersecurity remains elusive due to the absence of suitable benchmark environments and interaction datasets.