60 stories tagged with #language-models, in publish-time order across the WeSearch catalog. Tag pages update as new stories ingest.
⌘ RSS feed for this tag → or search "Language Models"
Rethinking Uncertainty Evaluation in Large Language Models
arXiv:2607.19367v1 Announce Type: new Abstract: Calibration is the primary criterion for evaluating LLM confidence, but it is insufficient: it admits trivially incoherent estimator…
Logic-Guided Data Extraction with Answer Set Programming and Large Language Models
arXiv:2607.19365v1 Announce Type: new Abstract: When Large Language Models (LLMs) are used for semantic data extraction from unstructured text, producing candidate relational facts…
Statistically Grounded Sparse-Feature Interventions for Activation-Space Control in Large Language Models
arXiv:2607.19364v1 Announce Type: new Abstract: Activation steering offers a lightweight alternative to fine-tuning for behavioral control of large language models, but SAE-based s…
Lifted Representation Hypothesis in Language Models
arXiv:2607.19360v1 Announce Type: new Abstract: Large language models (LLMs) often answer queries by mapping individual observations to more general rule-like structures. However, …
Information Discernment in Large Language Models
arXiv:2607.19355v1 Announce Type: new Abstract: LLMs are increasingly used with external knowledge sources like the internet. Do they weigh information appropriately -- updating mo…
Loop Engineering with Adaptive Parsing in Action: Parsing Flat Tables with Azure and Figures with a Vision LLM
Enterprise Document Intelligence [Vol.1 #10B] - The LLM as last line of defence, then two real escalations walked end to end: a flat table to Azure, a figure to a vision model The …
GPT-Red: an LLM super-hacker OpenAI built to make its models safer
Exclusive: The firm says it wants to future-proof its safety procedures and stay ahead of human attackers.…
Augmenting Fundamental Analysis with Large Language Models: A RAG-Based System for Generating Investor Briefs
In this study, we examine the opportunities brought by Large Language Models (LLMs) to various aspects of fundamental analysis of companies based on their reports as well as data a…
Integrating Large Language Models and Graph Convolutional Networks for Semi-Supervised Image Classification
While the growing availability of image data has driven significant advances, labeling datasets remains costly and time-consuming. Therefore, semi-supervised approaches such as Gra…
Accelerating GPU Inference of Large Language Models with Moderately Unstructured Sparse Weight Matrices
With the growing deployment of large language models (LLMs), LLM inference cost has become a key challenge. Pruning techniques that introduce sparsity into weight matrices can acce…
A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions
Despite the success of knowledge distillation (KD) in Large Language Models (LLMs), the underlying mechanism behind its efficacy remains unclear. In this paper, we propose a unifie…
Narration-of-Thought: Inference-Time Scaffolding for Defeasible Ethical Reasoning in Large Language Models
arXiv:2606.26366v1 Announce Type: new Abstract: Standard chain-of-thought on moral dilemmas exhibits two failure modes: stakeholder collapse (the trace names at most one party with…
Prompt Injection as Role Confusion
Prompt Injection as Role Confusion First, I absolutely love this: This is a blog-style writeup of the paper. I wish every paper would come with one of these. Academic writing is pr…
GPU Forecasters: Language Models as Selective Surrogates for Kernel Optimization
GPU kernels are the workhorse of modern deep learning, and optimizing them (via evolutionary search or coding agents) usually requires repeated measurement on target hardware. Whil…
Benchmarking LLM-as-a-Judge for Long-Form Output Evaluation
As large language models (LLMs) are increasingly used for long-form generation, reliably evaluating long-form outputs has become a critical challenge. LLM-as-a-judge offers a scala…
Code-on-Graph: Iterative Programmatic Reasoning via Large Language Models on Knowledge Graphs
Knowledge Graphs (KGs) are widely used to mitigate the limitations of Large Language Models (LLMs), such as outdated knowledge and hallucinations. Existing LLM-KG integration frame…
From Answers to States: Verifiable Process-Level Evaluation of Chemical Reasoning in Large Language Models
Large language models are increasingly used as chemistry assistants, yet most chemistry benchmarks still score only final answers. This masks a critical failure mode: a model may o…
ClinicalMC: A Benchmark for Multi-Course Clinical Decision-Making with Large Language Models
Large language models (LLMs) have been widely adopted in healthcare, yet they still encounter significant challenges in complex clinical decision-making scenarios. Existing benchma…
Uncertainty-Aware Clarification in LLM Agents with Information Gain
Large Language Model (LLM) agents often operate under underspecified user instructions, where latent uncertainty over user intent leads to erroneous tool actions. To address this c…
Decomposing how prompting steers behavior
Prompting steers large language models (LLMs) and vision-language models (VLMs) without weight updates, but it remains unclear how instruction changes reshape internal representati…
The Shadow Price of Reasoning: Economic Perspective on Optimal Budget Allocation for LLMs
Inference-time scaling has emerged as a critical avenue for enhancing Large Language Models' performance, yet real-world deployment is constrained by strict computational budgets. …
SkillDAG: Self-Evolving Typed Skill Graphs for LLM Skill Selection at Scale
As LLM agents adopt large skill libraries, selecting the right subset becomes a structural problem rather than a similarity-matching one: skills depend on, conflict with, specializ…
ChatHealthAI: Aligning Electronic Health Record Representations with Large Language Models for Grounded Clinical Reasoning
Large language models (LLMs) exhibit strong natural-language reasoning abilities for clinical decision support, but struggle to effectively model structured longitudinal electronic…
Visual Graph Scaffolds for Structural Reasoning in Large Language Models
Graphs have been used to enhance large language models (LLMs) for structured reasoning, mostly as external knowledge sources are provided to models at test time. In this paper, we …
Why Are Large Language Models So Terrible at Video Games?
LLMs can code your retro shooter but still fail at playing Halo; see what this gap reveals about AI’s real limits in 2026…
Scaling Laws for Agent Harnesses via Effective Feedback Compute
Agent harnesses increasingly determine the performance of language-model systems by deciding how models call tools, receive feedback, verify intermediate states, store memory, and …
Heuristic Parasites: A Behavioral Taxonomy of Recurrent Distortion Patterns in Large Language Models (Full System) V2
AI Propaganda factories with language models
AI-powered influence operations can now be executed end-to-end on commodity hardware. We show that small language models produce coherent, persona-driven political messaging and ca…
✨📊 🧠 The Ultimate Visual Guide to Large Language Models (LLMs)
Generative AI is a type of artificial intelligence that can produce new content including text,...…
📄Paper: RORA-VLM: Robust Retrieval Augmentation for Vision Language Models
Public At International Conference on Learning Representations (ICLR) 2025 💡 Why I read...…
LLMs believe false statements even after explicit warnings that they're false
Fine-tuning tests show "bias ... toward confidently representing the claims as true."…
Why does AI love writing about lighthouse keepers?
Asked to 'write a story', ChatGPT and other leading language models appear to be avoiding copyright infringement by obsessive recourse to the same small and strange cast of lightho…
How sure is the activation oracle?
Activation oracles aim to make the activations of other models legible to humans and yield promising results compared to white-box interpretability techniques. However, uncertainty…
PitchBench: Measuring Pitch Hearing in Audio-Language Models
Audio-language models (ALMs) are increasingly used in real-world applications that require understanding music, from music tutoring and transcription to captioning, recommendation …
Pretraining Data Exposure in Large Language Models: A Survey of Membership Inference, Data Contamination, and Security Implications
Large Language Models (LLMs) have become the predominant paradigm in NLP, advancing both research and industry. As model sizes and pretraining data grow, concerns about Pretraining…
Gumbel Machine: Counterfactual Student Writing Generation via Gumbel Noise Steering
An effective method of teaching across disciplines is to provide examples of high-quality work. However, an example may be significantly different from a student's current work, ma…
Detecting Is Not Resolving: The Monitoring Control Gap in Retrieval Augmented LLMs
Retrieval-augmented LLMs are deployed for tasks where evidence quality determines action safety, yet evaluation protocols assume that single-turn robustness predicts robustness whe…
Counteraction-Aware Multi-Teacher On-Policy Distillation for General Capability Recovery with Domain Preservation
Domain specialization can improve LLM behavior in vertical domains, but often weakens the general capabilities inherited from the original model. Recent Multi-Teacher On-Policy Dis…
Generating Robust Portfolios of Optimization Models using Large Language Models
Mathematical optimization is a powerful tool for structured decision-making across domains such as resource allocation and planning. Formulating optimization models faithful to rea…
Multi-Stakeholder LLM Alignment: Decomposing Estimation from Aggregation
Multi-stakeholder tasks require one output to satisfy users with conflicting preferences. Holistic LLM judges conflate utility estimation and utility aggregation, yielding unstable…
What Makes Chain-of-Thought Work at Probe Time? Local Co-occurrence Rather Than Global Derivation
Chain-of-thought (CoT) prompting reliably improves language-model accuracy, but which properties of a rationale text drive the improvement is poorly understood. Prior work has larg…
The Attribution Blind Spot: Detecting When Language Models Rely on Memory Rather Than Retrieved Context
Retrieval-augmented generation promises to ground language model outputs in external evidence, yet the field has no reliable way to verify whether retrieved context actually govern…
Towards Feedback-to-Plan Decisions for Self-Evolving LLM Agents in CUDA Kernel Generation
Large language models (LLMs) have shown strong empirical gains as self-evolving agents for CUDA kernel generation, driven by feedback-conditioned planning across generations. Howev…
AGORA: Adapter-Grounded Observation-Action Retention for Inference-Free Prompt Compression in LLM Agents
The token-level extractive compressors widely used for general LM context are structurally inappropriate for LLM agents: across 17 (env, backbone, method) cells spanning two indepe…
MedGuideX: Internalizing Decision Logic from Executable Guidelines into Large Language Models for Clinical Reasoning
Clinical practice guidelines (CPGs) encode evidence-based decision logic that clinicians apply by evaluating patient variables, conditional criteria, and recommendation rules. Howe…
The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence
We introduce the MiniMax-M2 series, a family of Mixture-of-Experts language models built around the principle that mini activations can unleash maximum real-world intelligence. The…
Reasoning, Code, or Both? How Large Language Models Handle Variations in Math Questions
Large Language Models (LLMs) achieve impressive accuracy on mathematical reasoning benchmarks, yet their performance drops when problems are modified with simple changes like diffe…
OmniToM: Benchmarking Theory of Mind in LLMs via Explicit Belief Modeling
Theory of Mind (ToM), the ability to infer others' knowledge, intentions, and emotions, is commonly evaluated in large language models (LLMs) using end-point question answering, wh…
Can LLMs Introspect? A Reality Check
Can large language models detect and report their own internal states? A number of studies have argued that the answer to this question is yes. We argue, based on lessons from huma…
Microsoft Research: LLMs Corrupt your files during delegated work
Large Language Models (LLMs) are poised to disrupt knowledge work, with the emergence of delegated work as a new interaction paradigm (e.g., vibe coding). Delegation requires trust…
Sparse Autoencoders Reveal Cortical Brain-LLM Semantic Mapping
A preprint submitted to arXiv (arXiv:2605.23035) by Dongxin Guo and colleagues presents a mechanistic interpretability approach connecting large language model representations to h…
Prompt Politeness Affects LLM Accuracy
The wording of natural language prompts has been shown to influence the performance of large language models (LLMs), yet the role of politeness and tone remains underexplored. In t…
You don't need all the LLM benchmarks
Credit Assignment with Resets in Language Model Reasoning
Contemporary reinforcement learning with verifiable reward methods post-train language models on multi-step reasoning by assigning a single outcome reward uniformly across all toke…
Second Guess: Detecting Uncertainty Through Abstention and Answer Stability in Small Language Models
Large language models often generate confident but incorrect answers rather than abstaining when uncertain. This problem is particularly acute for small language models (SLMs), whe…
DarkForest: Less Talk, Higher Accuracy for Multi-Agent LLMs
Multi-agent LLM systems improve reasoning by combining outputs from multiple agents, but interaction-heavy methods can introduce error propagation and high communication overhead. …
Representation Without Control: Testing the Realization Effect in Language Models
Large language models are increasingly used as behavioral simulators, but it remains unclear when their outputs reflect human-like cognitive mechanisms rather than prompt-sensitive…
Beyond the Frontier: Stochastic Backtracking for Efficient Test-Time Scaling
Test-time scaling improves language model reasoning by spending additional compute to explore multiple solution trajectories. The key challenge is to maximize accuracy while minimi…
Trust but Verify: Prover-Verifier Deliberation for Selective LLM Prediction
Reliably knowing when a language model is correct is almost as important as being correct. We introduce prover-verifier deliberation (PVD), an inference-time protocol grounded in i…
Privacy-Preserving Local Language Models for Longitudinal Data Retrieval in Chronic Dermatologic Disease: Implementation in Pemphigus Patients
Chronic dermatologic diseases such as pemphigus require long-term follow-up, generating extensive longitudinal clinical documentation that is difficult to review comprehensively du…