Papers

Field

Top tools here

Coming with more sources: stars history

All tools

NVIDIA Dynamo+60% downloads · 15.8k/wk+60.0%
Agno4 releases this week
FastMCP6 releases this week
BentoML+30% downloads · 41k/wk+29.7%
n8n+25% downloads · 148.3k/wk+25.0%

Top tools here

Open problems in Frontier LLMs

Structural requirements for decision-native models1 paper raises it · 1 addresses it
Current decision models often ignore key properties like null-awareness, permutation invariance, and option scalability, limiting their reliability and efficiency.
- Jeva: System One Models from First Principlesraises · addresses
Efficient and calibrated decision-making for search agents1 paper raises it · 1 addresses it
Generative models introduce latency and unreliable confidence in short, repeated decisions, hindering real-time search agent performance.
- SearchJev: A Fast and Calibrated System-1 Model for Search Agentsraises · addresses
Sustaining self-evolution in reasoning models1 paper raises it · 1 addresses it
Self-training on generated questions can collapse performance due to invalid or repetitive questions, limiting long-term improvement.
- Questioning the Questions: Sustaining Self-Evolution in Reasoning Modelsraises · addresses
Memory consolidation in context-conditioned models1 paper raises it · 1 addresses it
Gains from context are often lost after its removal, reducing the long-term utility of contextual learning.
- Cortex: Consolidating Context into Parametric Memoryraises · addresses
Detecting and mitigating scientific slop in AI-generated papers1 paper raises it · 1 addresses it
AI-generated scientific papers can appear plausible but contain flawed reasoning, misleading readers and degrading research quality.
- Science or Slop?: Benchmarking and Mitigating Scientific Slop in AI-Generated Papersraises · addresses

Named by an AI from these papers' abstracts.

Open problems

Recently funded

Market

InfinigenceSeries B+ · Oct 12$343.6M
Lean SuperIntelligencePre-seed · Oct 9undisclosed
VinciSeries B+ · Oct 6$250M
Siena AISeries A · Oct 6$17M
Ocular AIPre-seed · Oct 5$2M

Recently funded

Topics in this field

reasoning traces · reasoning models · latent reasoning381 papers65 this week
dense retrieval · retrieval augmented generation · retrieval256 papers52 this week
attention heads · large language models · language models231 papers51 this week
large language models · attribution · language models llms203 papers42 this week
question answering · answering · large language models140 papers40 this week
large language models · large language · language models184 papers38 this week

Topics in this field

Active contributors · 90 days

Active contributors

Activity · 12 weeks

Coming with more sources: repos

Activity

Recent papers

All in Research →

arXiv cs.CROct 17
Narratives Mislead: An Empirical Study of How LLMs Misjudge CVSS Severity in Bug Bounty Reports
Ruitao Feng, Yuekang Li, Yao Zhang
Bug bounty platforms receive vulnerability reports faster than vendors can triage them, and Large Language Models (LLMs) are increasingly considered for assigning the Common Vulnerability Scoring System (CVSS) severity that drives prioritization. Prior evaluations score short CVE descriptions and report accuracy, but deployment depends on how models err, not only how often. CVSS gives each metric a formal meaning that departs from how researchers describe impact in narrative reports, and model rationales suggest that errors concentrate where the two diverge; we ask whether this pattern is systematic. From 4,281 publicly disclosed reports mined from Huntr and HackerOne, we build a benchmark of 240 Huntr reports with vendor-validated CVSS vectors and evaluate eight LLMs under four prompting strategies and fine-tuning, measuring errors by severity class and score and analysing sub-vectors on individual reports. The best prompting configuration reaches only 49.58% level accuracy, ten points above always predicting the majority level, and fine-tuning a 7B model raises this to at most 56.25%, an optimistic upper bound. Errors are directional: models overestimate far more often than…
PDF arXiv
arXiv cs.LGOct 17
How Much Do Activation Monitors Benefit from Original Model Computations?
James Oldfield, Shawn Im, Jay J Culligan, Philip Torr, Sharon Li +1
One powerful way to safeguard AI systems is to monitor their internal computations--where signs of undesirable behavior might be more easily detectable than from models' inputs and outputs alone. However, recent studies begin to question the premise that activations provide a unique window into model behavior. In this paper, we study how much of activation monitors' success depends on access to the original behavior-generating computations. Within a fixed choice of target model and monitoring architecture, we compare how well monitors trained and evaluated on trajectories that differ in computational context can predict the behavior of the original execution, after the transcript is changed in a controlled manner (e.g., its exact text, or chat formatting). We first find that much performance can be recovered without access to the original behavior-generating trace (in up to 4 models across 2 counterfactual monitoring tasks), but a mild yet consistent advantage to native-trained monitors remains, outperforming strongest controls by up to 0.014 AUROC. Interestingly, we find monitors trained with native access have notable uplift on original examples whose behavioral label changes…
PDF arXiv
arXiv cs.SEOct 17
From Candidate Admission to Task-Level Return: Auditing LLM-Generated Code under Execution Contracts
Hiroyasu Usami, Keisuke Hara, Ayato Tsuboi, Naohiko Matsuda
Admission rules retain generated programs, whereas selection policies return one candidate per task. We audit how these decisions interact with execution contracts in two separately frozen, disjoint HumanEvalPlus cohorts, each comprising 32 tasks, four samples per task per profile and two served profiles. Under the inline execution contract, a structural-and-self-test screen admits 4-9 expanded-suite nonpasses per 80-107 admissions and excludes 14-43 suite passes per 128 planned attempts. A restricted module-supply condition adds 20 and 14 passing admissions for one profile in the respective cohorts, plus one follow-up nonpass, and reduces the excluded suite passes to 14-23. All fixed first-admitted outcomes and abstentions remain unchanged. In the original pool, the added passes enter already all-passing admitted pools; in the follow-up, four of 24 common sample orders lose one passed task. Selected-subset diagnostics separately address registration-sensitive completion and reference-relative assertion disagreement, accounting for input domains and comparator tolerances. In these high-pass pools, candidate retention and task-level return diverge and are reported separately.…
PDF arXiv
arXiv cs.CLOct 17
Training with Ciphers to Enhance In-Context Terminology Learning For Translation from Rare Languages
Deevyanshu Malu, Deeptanshu Malu, Sunita Sarawagi
Fine-tuning LLMs with in-context examples (IC-Train) lets translation models adapt to new parallel data at deployment, but it is unclear whether they actually learn the translations of rare terms from those examples. We formalize this capability as in-context term learning (ICTL). We show that standard IC-Train develops this capability only weakly, and propose RareCipherFT, which strengthens it without any lexical resources. RareCipherFT pairs each training target with in-context examples that share a rare term with it. It then replaces that term with a character-shuffled cipher in both the context and the reference, so the term can only be recovered by copying from context. The ciphered fraction of training data is annealed to preserve translation quality. Across seven translation directions between English and Tamil, Assamese, Mizo, Nepali and Hausa, and four models from 1B to 7B parameters, RareCipherFT raises term recall over standard IC-Train by 5-15 absolute points without lowering COMET. Probes using synonyms, nonce words and controls for shared surface context show that these gains come from linking source terms to their in-context translations rather than from shortcuts.
PDF arXiv
arXiv stat.MLOct 17
Conditional Weight of Evidence for Gradient-Boosted Credit Models: Estimation, Additivity and Its Relation to Adverse Action Reasons
Agus Sudjianto, Denis Burakov
Traditional weight of evidence assigns a credit characteristic a value based on its association with default across a population. Credit analysis also requires an assessment of that characteristic in the context of an individual applicant's record. We study conditional weight of evidence for this purpose. It measures the change in default log odds from observing a characteristic after the remaining credit information is known. Its sign identifies whether the characteristic adds adverse or favorable information for that applicant, and its magnitude measures the strength of that information. The same characteristic value can therefore receive different assessments for applicants with different payment histories or other credit attributes. We develop estimators using gradient-boosted trees and evaluate their accuracy in a bureau-style simulation. Regressions of the full model's predicted probabilities recover conditional evidence more accurately than separate models fitted to default outcomes, provided the full model is accurate. They also recover a deliberately constructed file-age effect whose direction varies with utilization and is often missed by marginal weight of evidence.…
PDF arXiv
arXiv cs.CLOct 17
From Stories to Features: Scaling Concept Vectors for AI Alignment & Interpretability
Dmitry Scherbakov, Oleg Chernikov, Victoria Khamash, Kirill Afendulev, Alexey Dontsov +3
We study feature vectors: directions in a language model's activation space that correspond to human-interpretable concepts, such as honesty or deception. Existing unsupervised methods like sparse autoencoders attempt to recover the whole feature space, often at the cost of feature quality and interpretability. We take a more pragmatic route: focusing on concepts relevant to AI safety and alignment, we generate synthetic concept-antagonist story pairs and use the difference of their mean model activations as a feature vector. We scale this approach to 1,036 alignment-relevant concepts using 2M synthetic stories across multiple languages and genres, which we publicly release. Across six models from three model families, our feature vectors reliably generalize to detecting their corresponding concepts in chat dialogues and web text. They form an interpretable geometry shared across models and can causally steer model behavior when injected into activations. We further use these features to analyze model representations during jailbreak attacks, mathematical and agentic reasoning. Our targeted feature construction thus offers a scalable route to studying concepts in language models,…
PDF arXiv

Papers

Top tools here

Coming with more sources: stars history

All tools

NVIDIA Dynamo+60% downloads · 15.8k/wk+60.0%
Agno4 releases this week
FastMCP6 releases this week
BentoML+30% downloads · 41k/wk+29.7%
n8n+25% downloads · 148.3k/wk+25.0%

Recently funded

Market

InfinigenceSeries B+ · Oct 12$343.6M
Lean SuperIntelligencePre-seed · Oct 9undisclosed
VinciSeries B+ · Oct 6$250M
Siena AISeries A · Oct 6$17M
Ocular AIPre-seed · Oct 5$2M

Topics in this field

reasoning traces · reasoning models · latent reasoning381 papers65 this week
dense retrieval · retrieval augmented generation · retrieval256 papers52 this week
attention heads · large language models · language models231 papers51 this week
large language models · attribution · language models llms203 papers42 this week
question answering · answering · large language models140 papers40 this week
large language models · large language · language models184 papers38 this week

Active contributors · 90 days

Activity · 12 weeks

Coming with more sources: repos

Fields · AI · updated 53m ago

Frontier LLMs

The largest general-purpose language models, their releases, capabilities, scaling and training at frontier scale.

447papers this week−7.8% vs last week

All papers · 2.3k With code · 54

Newest Most relevant

2.2k papers this month

Recent papers

All in Research →

arXiv cs.CROct 17
Narratives Mislead: An Empirical Study of How LLMs Misjudge CVSS Severity in Bug Bounty Reports
Ruitao Feng, Yuekang Li, Yao Zhang
Bug bounty platforms receive vulnerability reports faster than vendors can triage them, and Large Language Models (LLMs) are increasingly considered for assigning the Common Vulnerability Scoring System (CVSS) severity that drives prioritization. Prior evaluations score short CVE descriptions and report accuracy, but deployment depends on how models err, not only how often. CVSS gives each metric a formal meaning that departs from how researchers describe impact in narrative reports, and model rationales suggest that errors concentrate where the two diverge; we ask whether this pattern is systematic. From 4,281 publicly disclosed reports mined from Huntr and HackerOne, we build a benchmark of 240 Huntr reports with vendor-validated CVSS vectors and evaluate eight LLMs under four prompting strategies and fine-tuning, measuring errors by severity class and score and analysing sub-vectors on individual reports. The best prompting configuration reaches only 49.58% level accuracy, ten points above always predicting the majority level, and fine-tuning a 7B model raises this to at most 56.25%, an optimistic upper bound. Errors are directional: models overestimate far more often than…
PDF arXiv
arXiv cs.LGOct 17
How Much Do Activation Monitors Benefit from Original Model Computations?
James Oldfield, Shawn Im, Jay J Culligan, Philip Torr, Sharon Li +1
One powerful way to safeguard AI systems is to monitor their internal computations--where signs of undesirable behavior might be more easily detectable than from models' inputs and outputs alone. However, recent studies begin to question the premise that activations provide a unique window into model behavior. In this paper, we study how much of activation monitors' success depends on access to the original behavior-generating computations. Within a fixed choice of target model and monitoring architecture, we compare how well monitors trained and evaluated on trajectories that differ in computational context can predict the behavior of the original execution, after the transcript is changed in a controlled manner (e.g., its exact text, or chat formatting). We first find that much performance can be recovered without access to the original behavior-generating trace (in up to 4 models across 2 counterfactual monitoring tasks), but a mild yet consistent advantage to native-trained monitors remains, outperforming strongest controls by up to 0.014 AUROC. Interestingly, we find monitors trained with native access have notable uplift on original examples whose behavioral label changes…
PDF arXiv
arXiv cs.SEOct 17
From Candidate Admission to Task-Level Return: Auditing LLM-Generated Code under Execution Contracts
Hiroyasu Usami, Keisuke Hara, Ayato Tsuboi, Naohiko Matsuda
Admission rules retain generated programs, whereas selection policies return one candidate per task. We audit how these decisions interact with execution contracts in two separately frozen, disjoint HumanEvalPlus cohorts, each comprising 32 tasks, four samples per task per profile and two served profiles. Under the inline execution contract, a structural-and-self-test screen admits 4-9 expanded-suite nonpasses per 80-107 admissions and excludes 14-43 suite passes per 128 planned attempts. A restricted module-supply condition adds 20 and 14 passing admissions for one profile in the respective cohorts, plus one follow-up nonpass, and reduces the excluded suite passes to 14-23. All fixed first-admitted outcomes and abstentions remain unchanged. In the original pool, the added passes enter already all-passing admitted pools; in the follow-up, four of 24 common sample orders lose one passed task. Selected-subset diagnostics separately address registration-sensitive completion and reference-relative assertion disagreement, accounting for input domains and comparator tolerances. In these high-pass pools, candidate retention and task-level return diverge and are reported separately.…
PDF arXiv
arXiv cs.CLOct 17
Training with Ciphers to Enhance In-Context Terminology Learning For Translation from Rare Languages
Deevyanshu Malu, Deeptanshu Malu, Sunita Sarawagi
Fine-tuning LLMs with in-context examples (IC-Train) lets translation models adapt to new parallel data at deployment, but it is unclear whether they actually learn the translations of rare terms from those examples. We formalize this capability as in-context term learning (ICTL). We show that standard IC-Train develops this capability only weakly, and propose RareCipherFT, which strengthens it without any lexical resources. RareCipherFT pairs each training target with in-context examples that share a rare term with it. It then replaces that term with a character-shuffled cipher in both the context and the reference, so the term can only be recovered by copying from context. The ciphered fraction of training data is annealed to preserve translation quality. Across seven translation directions between English and Tamil, Assamese, Mizo, Nepali and Hausa, and four models from 1B to 7B parameters, RareCipherFT raises term recall over standard IC-Train by 5-15 absolute points without lowering COMET. Probes using synonyms, nonce words and controls for shared surface context show that these gains come from linking source terms to their in-context translations rather than from shortcuts.
PDF arXiv
arXiv stat.MLOct 17
Conditional Weight of Evidence for Gradient-Boosted Credit Models: Estimation, Additivity and Its Relation to Adverse Action Reasons
Agus Sudjianto, Denis Burakov
Traditional weight of evidence assigns a credit characteristic a value based on its association with default across a population. Credit analysis also requires an assessment of that characteristic in the context of an individual applicant's record. We study conditional weight of evidence for this purpose. It measures the change in default log odds from observing a characteristic after the remaining credit information is known. Its sign identifies whether the characteristic adds adverse or favorable information for that applicant, and its magnitude measures the strength of that information. The same characteristic value can therefore receive different assessments for applicants with different payment histories or other credit attributes. We develop estimators using gradient-boosted trees and evaluate their accuracy in a bureau-style simulation. Regressions of the full model's predicted probabilities recover conditional evidence more accurately than separate models fitted to default outcomes, provided the full model is accurate. They also recover a deliberately constructed file-age effect whose direction varies with utilization and is often missed by marginal weight of evidence.…
PDF arXiv
arXiv cs.CLOct 17
From Stories to Features: Scaling Concept Vectors for AI Alignment & Interpretability
Dmitry Scherbakov, Oleg Chernikov, Victoria Khamash, Kirill Afendulev, Alexey Dontsov +3
We study feature vectors: directions in a language model's activation space that correspond to human-interpretable concepts, such as honesty or deception. Existing unsupervised methods like sparse autoencoders attempt to recover the whole feature space, often at the cost of feature quality and interpretability. We take a more pragmatic route: focusing on concepts relevant to AI safety and alignment, we generate synthetic concept-antagonist story pairs and use the difference of their mean model activations as a feature vector. We scale this approach to 1,036 alignment-relevant concepts using 2M synthetic stories across multiple languages and genres, which we publicly release. Across six models from three model families, our feature vectors reliably generalize to detecting their corresponding concepts in chat dialogues and web text. They form an interpretable geometry shared across models and can causally steer model behavior when injected into activations. We further use these features to analyze model representations during jailbreak attacks, mathematical and agentic reasoning. Our targeted feature construction thus offers a scalable route to studying concepts in language models,…
PDF arXiv

Open problems in Frontier LLMs

Structural requirements for decision-native models1 paper raises it · 1 addresses it
Current decision models often ignore key properties like null-awareness, permutation invariance, and option scalability, limiting their reliability and efficiency.
- Jeva: System One Models from First Principlesraises · addresses
Efficient and calibrated decision-making for search agents1 paper raises it · 1 addresses it
Generative models introduce latency and unreliable confidence in short, repeated decisions, hindering real-time search agent performance.
- SearchJev: A Fast and Calibrated System-1 Model for Search Agentsraises · addresses
Sustaining self-evolution in reasoning models1 paper raises it · 1 addresses it
Self-training on generated questions can collapse performance due to invalid or repetitive questions, limiting long-term improvement.
- Questioning the Questions: Sustaining Self-Evolution in Reasoning Modelsraises · addresses
Memory consolidation in context-conditioned models1 paper raises it · 1 addresses it
Gains from context are often lost after its removal, reducing the long-term utility of contextual learning.
- Cortex: Consolidating Context into Parametric Memoryraises · addresses
Detecting and mitigating scientific slop in AI-generated papers1 paper raises it · 1 addresses it
AI-generated scientific papers can appear plausible but contain flawed reasoning, misleading readers and degrading research quality.
- Science or Slop?: Benchmarking and Mitigating Scientific Slop in AI-Generated Papersraises · addresses

Named by an AI from these papers' abstracts.