Category
3,231 papers
Findings provide evidence that truthfulness is a structured, linearly separable concept in the latent space of pretrained language models, and point toward interpretability-driven misinformation detection as a practical complement to retrieval-based pipelines.
The overall results show that editable, consolidated memory can supply remembered context for robot planning, and full MEMORA--combining editing, typed stores, and consolidation--achieves the strongest aggregate results among the evaluated memory conditions.
A supervised ensembling framework that trains a classifier over heterogeneous UQ-based scorer outputs on a small, domain-specific dataset of labeled LLM responses, then applies it to out-of-sample hallucination classification without retrieval, tools, or reference documents is studied.
This work introduces a general steering technique called Semantic Overlays: small learned adapters applied at chosen prefill positions to a frozen model's residual stream that defends against the broad class of prompt injections that add instructions in untrusted context.
Reach audiences
Advertise in front of researchers, engineers, and readers.
Results indicate that current LLMs provide uneven safety assurance across Urdu's script varieties, with smaller open-weight models showing substantially higher instability and missed-harm rates than frontier closed models.
Dual-Layer Agentic Memory is proposed, a framework that shifts memory management to the write phase through cost-aware epistemic routing and periodic parametric consolidation, allowing the router to adaptively suppress redundant writes as the model's epistemic boundaries evolve.
SyRuP is introduced, a decoding-time framework for improving system-prompt adherence while keeping the base LM frozen, and results suggest that explicit token-level guidance is an effective and practical mechanism for reliable system-prompt following.
It is shown that mechanistic diagnosis can serve as a practical guide for targeted adaptation in underrepresented-language medical LLMs, and Targeted Low-Rank Adaptation (TLoRA) is proposed, restricted to the layer window where cross-lingual representations diverge, upstream of the output layers where the failure manifests.
An automated TCS research framework that generates, formalizes, filters, and proves new claims, and further develops an automated TCS research framework that generates, formalizes, filters, and proves new claims.
AdaFlash framework is proposed, comprising two components: an on-policy distillation algorithm with reverse-KL divergence tailored for diffusion drafters, bringing stable convergence and effectively reducing domain-level variance and an adaptive length head that dynamically adjusts the candidate sequence length on the fly, substantially lowering the verification cost of the target model and handling token-level variance.
These findings show that reliable evaluation of LLM-generated code requires validated ground truth, protected tests, and multiple explicitly interpreted measures, and that CodeAssay provides a reproducible basis for evidence-based model evaluation in AI-augmented software development.
Emergent misalignment (EM) is the phenomenon where fine-tuning a language model on a narrow task leads to harmful behavior in unrelated domains. A leading mechanistic account attributes EM to persona features: latent directions acquired during pre-training that misaligned fine-tuning amplifies. We ask where these features come from: which pre-training documents activate them, and whether naturally occurring human-written text suffices to induce EM. Using Sparse Autoencoder (SAE) based model diffing across four open-weight models, we find that features related to jailbreak personas, sarcasm, deception, and manipulation are amplified by misalignment fine-tuning, while safety-relevant and assistant-identity features are suppressed. Steering individual features controls EM in both directions: it induces misalignment rates of up to 62% in aligned models -- exceeding the 35% reached by misalignment fine-tuning itself -- and re-aligns misaligned models to near-baseline misalignment rates. Attributing the causal features to a corpus of one million pre-training web documents retrieves semantically relevant narratives about villainous characters, domination, and harmful agency. However, fine-tuning on these human-written documents does not reliably induce EM, even after reformatting into assistant-style responses, whereas synthetic instruction-response pairs derived from the same content do -- and transfer across model families. Semantic relevance alone is therefore not sufficient: response structure or model-generated phrasing plays an important role in inducing EM.
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.
A new machine-learning framework aims to improve the success rate of computational protein design while moving away from results that reproduce sequences found in nature.
Algorithms & Theory
New MIT research could lead to better materials for a fossil-fuel-free process for making the chemical that's essential to fertilizer and other products.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
