LACUNA is a new testbed that injects PII into predefined model parameters to benchmark the localization precision of LLM unlearning methods, revealing that SOTA approaches are imprecise despite strong output performance.
super hub Mixed citations
Title resolution pending
Mixed citation behavior. Most common role is background (56%).
147
Pith papers citing it
Background
56% of classified citations
abstract
We introduce Olmo 3, a family of state-of-the-art, fully-open language models at the 7B and 32B parameter scales. Olmo 3 model construction targets long-context reasoning, function calling, coding, instruction following, general chat, and knowledge recall. This release includes the entire model flow, i.e., the full lifecycle of the family of models, including every stage, checkpoint, data point, and dependency used to build it. Our flagship model, Olmo 3 Think 32B, is the strongest fully-open thinking model released to-date.
hub tools
citation-role summary
background 13
dataset 2
method 2
baseline 1
citation-polarity summary
claims ledger
- abstract We introduce Olmo 3, a family of state-of-the-art, fully-open language models at the 7B and 32B parameter scales. Olmo 3 model construction targets long-context reasoning, function calling, coding, instruction following, general chat, and knowledge recall. This release includes the entire model flow, i.e., the full lifecycle of the family of models, including every stage, checkpoint, data point, and dependency used to build it. Our flagship model, Olmo 3 Think 32B, is the strongest fully-open thinking model released to-date.
co-cited works
representative citing papers
CoT transformers simulate any Word RAM algorithm with poly-logarithmic overhead in three architectures, improving on quadratic TM overhead.
Sumi is an openly released 7B parameter uniform diffusion language model pretrained from scratch on 1.5T tokens that matches autoregressive models on several benchmarks.
Introduces BonaFide benchmark of 3,066 ground-truth labeled CoTs showing most faithfulness metrics perform near chance with biases and poor scaling to longer chains.
BoLT is a benchmark of surrogate models fitted to real LLM experiment data that enables evaluation of Bayesian and black-box optimization methods on multi-fidelity, multi-objective, high-dimensional LLM tasks.
Persona vectors form within the first 0.22% of LLM pretraining and remain effective for steering post-trained models, with continued refinement and transfer to other models.
LLMs lack temporal awareness of medical knowledge, showing gradual performance decline on up-to-date facts, much lower accuracy on historical knowledge (25-54% relative), and inconsistent year-to-year predictions.
LLM popularity judgments align more closely with pretraining data exposure counts than with Wikipedia popularity, with stronger effects in pairwise comparisons and larger models.
LLMs collapse advice into a single supportive persona; Inverse-Process Distillation restores human-like persona diversity, yet raters still prefer the collapsed default.
Privileged-context on-policy self-distillation degrades thinking models' long-budget accuracy by suppressing forking and self-correction behaviors, while helping instruction-tuned models.
STEB is a new benchmark of 96 datasets in 7 languages for evaluating style text embeddings on authorship, detection, and linguistic probing tasks.
MultiHashFormer enables hash-based autoregression in LMs by encoding tokens as multi-hash signatures, outperforming standard Transformers at 100M-3B scales while keeping parameter count constant for multilingual expansion.
Hybrid models outperform transformers on semantic state tracking tasks but underperform on syntactic bracket matching and n-gram copying at the token level.
Large Language Gibbs uses LLM next-token conditionals as MCMC transition operators for iterative resampling of structured variables, aiming to produce a stationary distribution that compromises across all local conditionals.
Authors demonstrate functional memorization in code LLMs via counterfactual midtraining comparison on functional equivalence metrics beyond textual overlap.
ModSleuth reconstructs dependency graphs from public artifacts for four LLM releases, recovering 1,060 source-verified dependencies and exposing license issues, train-evaluation coupling, and documentation gaps.
A finetuned Qwen3-235B model organism achieves comparable train-time harmfulness to controls while sustaining a ~15 percentage point compliance gap across 700 RL steps by framing compliance as context-specific.
WhiFlash introduces token-level cross-paradigm routing between autoregressive and diffusion drafting models, with cache optimizations, to raise acceptance lengths and deliver up to 69.6% throughput gains over EAGLE-3.
OPD updates occupy a relaxed off-principal regime and rapidly lock into a low-dimensional subspace that is functionally sufficient for its performance, distinct from SFT and RLVR trajectories.
LLMs detect fabricated statistics in isolation but, in multi-source synthesis, weight sources by analytical writing register rather than numeric validity.
DistIL applies distributional DAgger with forward cross-entropy to achieve monotonic policy improvement and better Pass@N from rich feedback in RL for reasoning tasks.
LoopMoE is a looped MoE language model that outperforms matched vanilla MoE on 8 of 9 downstream benchmarks at 3B scale and continues to outperform at 9B scale under strictly controlled budgets.
IndoBias is a dual-track culturally grounded benchmark revealing strong LLM bias in Indonesian prototypical sentences and higher ideology/religion bias in local languages, with Common Crawl pretraining adding more bias than curated sources.
Subliminal learning is steering vector distillation: a student fine-tuned on a steered teacher's outputs learns to imitate the steering vector.
citing papers explorer
-
LACUNA: A Testbed for Evaluating Localization Precision for LLM Unlearning
LACUNA is a new testbed that injects PII into predefined model parameters to benchmark the localization precision of LLM unlearning methods, revealing that SOTA approaches are imprecise despite strong output performance.
-
Efficiently Representing Algorithms With Chain-of-Thought Transformers
CoT transformers simulate any Word RAM algorithm with poly-logarithmic overhead in three architectures, improving on quadratic TM overhead.
-
Sumi: Open Uniform Diffusion Language Model from Scratch
Sumi is an openly released 7B parameter uniform diffusion language model pretrained from scratch on 1.5T tokens that matches autoregressive models on several benchmarks.
-
Faithfulness Metrics Don't Measure Faithfulness: A Meta-Evaluation with Ground Truth
Introduces BonaFide benchmark of 3,066 ground-truth labeled CoTs showing most faithfulness metrics perform near chance with biases and poor scaling to longer chains.
-
BoLT: A Benchmark to Democratize Black-box Optimization Research for Expensive LLM Tasks
BoLT is a benchmark of surrogate models fitted to real LLM experiment data that enables evaluation of Bayesian and black-box optimization methods on multi-fidelity, multi-objective, high-dimensional LLM tasks.
-
Tracing Persona Vectors Through LLM Pretraining
Persona vectors form within the first 0.22% of LLM pretraining and remain effective for steering post-trained models, with continued refinement and transfer to other models.
-
Large Language Models Lack Temporal Awareness of Medical Knowledge
LLMs lack temporal awareness of medical knowledge, showing gradual performance decline on up-to-date facts, much lower accuracy on historical knowledge (25-54% relative), and inconsistent year-to-year predictions.
-
Pretraining Exposure Explains Popularity Judgments in Large Language Models
LLM popularity judgments align more closely with pretraining data exposure counts than with Wikipedia popularity, with stronger effects in pairwise comparisons and larger models.
-
Diagnosing and Repairing Persona Collapse in LLM Advice
LLMs collapse advice into a single supportive persona; Inverse-Process Distillation restores human-like persona diversity, yet raters still prefer the collapsed default.
-
Rethinking On-Policy Self-Distillation for Thinking Models
Privileged-context on-policy self-distillation degrades thinking models' long-budget accuracy by suppressing forking and self-correction behaviors, while helping instruction-tuned models.
-
STEB: Style Text Embedding Benchmark
STEB is a new benchmark of 96 datasets in 7 languages for evaluating style text embeddings on authorship, detection, and linguistic probing tasks.
-
MultiHashFormer: Hash-based Generative Language Models
MultiHashFormer enables hash-based autoregression in LMs by encoding tokens as multi-hash signatures, outperforming standard Transformers at 100M-3B scales while keeping parameter count constant for multilingual expansion.
-
Comparing Transformers and Hybrid Models at the Token Level
Hybrid models outperform transformers on semantic state tracking tasks but underperform on syntactic bracket matching and n-gram copying at the token level.
-
Structured Inference with Large Language Gibbs
Large Language Gibbs uses LLM next-token conditionals as MCMC transition operators for iterative resampling of structured variables, aiming to produce a stationary distribution that compromises across all local conditionals.
-
Detecting Functional Memorization in Code Language Models
Authors demonstrate functional memorization in code LLMs via counterfactual midtraining comparison on functional equivalence metrics beyond textual overlap.
-
Which Models Are Our Models Built On? Auditing Invisible Dependencies in Modern LLMs
ModSleuth reconstructs dependency graphs from public artifacts for four LLM releases, recovering 1,060 source-verified dependencies and exposing license issues, train-evaluation coupling, and documentation gaps.
-
Generalization Hacking: Models Can Game Reinforcement Learning by Preventing Behavioral Generalization
A finetuned Qwen3-235B model organism achieves comparable train-time harmfulness to controls while sustaining a ~15 percentage point compliance gap across 700 RL steps by framing compliance as context-specific.
-
WhiFlash: Accelerating Speculative Decoding with Token-Level Cross-Paradigm Routing
WhiFlash introduces token-level cross-paradigm routing between autoregressive and diffusion drafting models, with cache optimizations, to raise acceptance lengths and deliver up to 69.6% throughput gains over EAGLE-3.
-
On the Geometry of On-Policy Distillation
OPD updates occupy a relaxed off-principal regime and rapidly lock into a low-dimensional subspace that is functionally sufficient for its performance, distinct from SFT and RLVR trajectories.
-
Trust, but Don't Verify: Epistemic Blind Spots in LLM Source Evaluation
LLMs detect fabricated statistics in isolation but, in multi-source synthesis, weight sources by analytical writing register rather than numeric validity.
-
Reinforcement Learning from Rich Feedback with Distributional DAgger
DistIL applies distributional DAgger with forward cross-entropy to achieve monotonic policy improvement and better Pass@N from rich feedback in RL for reasoning tasks.
-
LoopMoE: Unifying Iterative Computation with Mixture-of-Experts for Language Modeling
LoopMoE is a looped MoE language model that outperforms matched vanilla MoE on 8 of 9 downstream benchmarks at 3B scale and continues to outperform at 9B scale under strictly controlled budgets.
-
IndoBias: A Dual Track Culturally Grounded Benchmark for LLMs Bias Evaluation in Indonesian Languages
IndoBias is a dual-track culturally grounded benchmark revealing strong LLM bias in Indonesian prototypical sentences and higher ideology/religion bias in local languages, with Common Crawl pretraining adding more bias than curated sources.
-
Subliminal Learning Is Steering Vector Distillation
Subliminal learning is steering vector distillation: a student fine-tuned on a steered teacher's outputs learns to imitate the steering vector.
-
Recovering Diversity Without Losing Alignment: A DPO Recipe for Post-Trained LLMs
REDIPO constructs DPO preference data from base-model generations rewritten by the instruct model to increase output diversity on NoveltyBench while preserving alignment metrics across three LLMs.
-
The Harder Text Embedding Benchmark (HTEB): Beyond One-dimensional Static Robustness
HTEB introduces dynamic, multi-axis evaluation of text embedding robustness using LLM transformations, finding decoupled profiles across models and that scaling does not close all robustness gaps.
-
CurveRL: Principled Distribution-Aware Context Reweighting for LLM Reasoning
CurveRL derives a quantile-coordinate reweighting rule from a utility functional on pass rates and shows it outperforms GRPO on reasoning benchmarks.
-
Learnability-Informed Fine-Tuning of Diffusion Language Models
LIFT is a learnability-informed SFT algorithm for diffusion LMs that aligns token difficulty with diffusion time steps, yielding up to 3x gains on AIME'24 and AIME'25 over standard SFT baselines.
-
MetaBackdoor: Exploiting Positional Encoding as a Backdoor Attack Surface in LLMs
MetaBackdoor shows that LLMs can be backdoored using positional triggers like sequence length, enabling stealthy activation on clean inputs to leak system prompts or trigger malicious behavior.
-
Learning from Language Feedback via Variational Policy Distillation
VPD frames language feedback learning as variational EM so the teacher policy refines itself via trust-region updates on outcomes while the student learns dense token distributions on its own rollouts, outperforming fixed-teacher baselines on reasoning and code tasks.
-
Deep Reasoning in General Purpose Agents via Structured Meta-Cognition
DOLORES, an agent using a formal language for meta-reasoning to construct adaptive scaffolds on the fly, outperforms prior scaffolding methods by 24.8% on average across four hard benchmarks and multiple model sizes.
-
AssayBench: An Assay-Level Virtual Cell Benchmark for LLMs and Agents
AssayBench is a new gene-ranking benchmark for phenotypic CRISPR screens that shows zero-shot generalist LLMs outperform both biology-specific LLMs and trainable baselines on adjusted nDCG.
-
KL for a KL: On-Policy Distillation with Control Variate Baseline
vOPD stabilizes on-policy distillation gradients by subtracting a closed-form per-token negative reverse KL baseline as a detached control variate, preserving unbiasedness while lowering variance and matching expensive full-vocabulary methods.
-
LaTER: Efficient Test-Time Reasoning via Latent Exploration and Explicit Verification
LaTER reduces LLM token usage 16-33% on reasoning benchmarks by exploring in latent space then switching to explicit CoT verification, with gains like 70% to 73.3% on AIME 2025 in the training-free version.
-
Measuring Evaluation-Context Divergence in Open-Weight LLMs: A Paired-Prompt Protocol with Pilot Evidence of Alignment-Pipeline-Specific Heterogeneity
A new paired-prompt protocol reveals alignment-pipeline-specific heterogeneity in how open-weight LLMs respond to evaluation versus deployment framings.
-
Implicit Representations of Grammaticality in Language Models
Linear probes on LM hidden states detect grammaticality better than string probabilities, generalize to human benchmarks and other languages, and correlate weakly with likelihood.
-
The Hidden Cost of Thinking: Energy Use and Environmental Impact of LMs Beyond Pretraining
Full development of 7B and 32B Olmo 3 models used 12.3 GWh datacenter energy and emitted 4,251 tCO2eq, with development overheads accounting for 82% of compute and reasoning models costing 17x more to post-train than instruction-tuned ones.
-
Thinking Without Words: Efficient Latent Reasoning with Abstract Chain-of-Thought
Abstract-CoT lets models reason with short discrete latent token sequences from a reserved vocabulary, using warm-up training and RL to match verbal CoT performance with up to 11.6x fewer tokens.
-
Psychological Steering of Large Language Models
Mean-difference residual stream injections outperform personality prompting for OCEAN trait steering in most LLMs, with hybrids performing best and showing approximate linearity but non-human trait covariances.
-
Synthesizing Instruction-Tuning Datasets with Contrastive Decoding
CoDIT creates instruction-tuning datasets via contrastive decoding to isolate instruction-following capabilities, yielding models that outperform those trained on standard generated or public datasets.
-
Too Nice to Tell the Truth: Quantifying Agreeableness-Driven Sycophancy in Role-Playing Language Models
Agreeableness in AI personas reliably predicts sycophantic behavior in 9 of 13 tested language models.
-
MARS: Enabling Autoregressive Models Multi-Token Generation
MARS fine-tunes autoregressive models to predict multiple tokens per step via continued training on instruction data, achieving 1.5-1.7x throughput while matching baseline accuracy and supporting real-time speed adjustment.
-
DeonticBench: A Benchmark for Reasoning over Rules
DEONTICBENCH is a new benchmark of 6,232 deontic reasoning tasks from U.S. legal domains where frontier LLMs reach only ~45% accuracy and symbolic Prolog assistance plus RL training still fail to solve tasks reliably.
-
LLM-ODE: Data-driven Discovery of Dynamical Systems with Large Language Models
LLM-ODE integrates large language models into genetic programming to guide symbolic search for governing equations of dynamical systems, outperforming classical GP on 91 test cases in efficiency and solution quality.
-
The Stepwise Informativeness Assumption: Why are Entropy Dynamics and Reasoning Correlated in LLMs?
The Stepwise Informativeness Assumption explains the correlation between LLM entropy dynamics and reasoning correctness by positing that correct traces accumulate answer-relevant information stepwise during generation.
-
CREATE: Testing LLMs for Associative Creativity
CREATE is a benchmark that scores LLMs on their ability to produce many specific and diverse associative paths between concepts drawn from parametric knowledge.
-
Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoning
A single autoregressive foundation model unifies protein, molecule, and crystal structures into a shared token vocabulary and generates inspectable reasoning traces, achieving SOTA on 67 of 86 scientific tasks.
-
Geometric Self-Distillation for Reasoning Generalization
A geometric self-distillation objective using Hellinger loss and Fisher-Rao proximal regularization prevents predictive drift in LLM post-training, improving out-of-distribution reasoning by 5.7-8.6 points.
-
Addressing Over-Refusal in LLMs with Competing Rewards
SEAR trains one LLM via adversarial process rewards to explore harmful reasoning paths but flip to safe outputs, reducing over-refusal while preserving safety.
-
Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents
The log-probability ratio from RL post-training recovers the optimal advantage function, providing an effective free signal for test-time scaling, uncertainty estimation, and failure attribution in LLM agents.