Category
7,546 papers
Proof-of-concept evidence that strong single-turn safety does not necessarily persist during sustained adversarial interaction is provided, highlighting the need for long-horizon evaluations and conversation-level safeguards that account for risk accumulating across turns.
The shared task is a shared task for evaluating hallucination detection and factual verification in Arabic question answering under challenging generalization settings, based on two Arabic datasets: HalluScore and HalluTruthQA.
Large language models (LLMs) are increasingly used to answer questions about politically contentious issues, yet evaluations typically treat a model's stance as a relatively stable property. Real users, however, communicate political signals through their terminology, assumptions, and personal context. We investigate w...
Long-running tools can dominate coding-agent latency: compilers, test suites, and repository commands take seconds to minutes while the agent idles. This observation stall presents the same tension that drove out-of-order processors -- asequential interface hides work that can be predicted and started early, but a spec...
Reach audiences
Advertise in front of researchers, engineers, and readers.
Survprompt is introduced, a framework that converts structured patient covariates into free-text clinical vignettes and prompts pre-trained LLMs to predict survival zero-shot, and feature ablations revealed that LLMs prioritized clinical variables similarly to specialized survival models.
Large language models (LLMs) are increasingly deployed as agents for multi-step decision-making, yet transfer poorly to unseen environments. World-model methods address this by training agents to predict future observations, at the cost of additional training and errors that compound when predictions are used for plann...
Reusable Latent Correction (RLC) is proposed, which converts one-off natural-language guidance from a black-box LLM into persistent corrective experiences in the hidden space of an SLM, enabling the SLM to reuse LLM-derived corrections during inference without any online LLM calls.
Comparing empirical cross-lingual transfer with typology-based similarity, it is found that transfer BLEU identifies closely interacting language pairs better than URIEL similarity, though neither predicts which varieties benefit from joint training.
NAMOH, an architecture-native sparse attention mechanism that activates only its assigned tokens and performs causal attention within this subsequence, is introduced, and it is hoped this work offers a new path for scaling attention, with parameter scaling directly enabling context scaling.
The rapid development of AI-driven tools, particularly large language models (LLMs), is reshaping professional writing. Still, key aspects of their adoption such as language support, ethics, and long-term impact on writers' voice and creativity remain underexplored. In this work, we carried out a questionnaire (N = 301...
Large language models (LLMs) are increasingly deployed as automated judges for AI-generated content, yet a single judge is unreliable and even a panel of judges leaves a hard residue: when judges disagree, majority voting discards the conflict instead of resolving it. We present JuryFlow, a disagreement-guided, human-i...
Existing full-duplex speech benchmarks cover only subsets of real-time interaction behaviors, often under limited contextual conditions. We introduce DuplexAct-Bench, a bilingual benchmark that systematically covers six complementary behaviors, from interruption and yielding to proactive initiation, active silence, and...
A new language-processing tool could help identify the highest-risk individuals from natural language, enabling swifter interventions.
A Blog post by Liquid AI on Hugging Face
Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking are our most advanced live dialogue models yet, built for natural conversation.
A new method, called CW-Net, translates the reasoning process of an autonomous vehicle’s AI system into understandable concepts that explain its behavior.
With millions of users across the world, Julia has been used to conduct cutting-edge research and to design new drugs, jet engines, heat pumps, and more.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
