No article text was recorded for this version.
internal-external knowledge gap
Version 1 of 1199 papers267 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Inside-Out: Hidden Factual Knowledge in LLMs
- Blog: Can Language Model Understand Word Semantics as A Chatbot? An Empirical Study of Language Model Internal External Mismatch
- Blog: Unravelling the Mechanisms of Manipulating Numbers in Language Models
- Blog: Analyzing LLMs' Knowledge Boundary Cognition Across Languages Through the Lens of Internal Representations
- Blog: A Comprehensive Evaluation of Constrained Text Generation for Large Language Models
- Blog: Insights into LLM Long-Context Failures: When Transformers Know but Don't Tell
- Blog: Trick or Neat: Adversarial Ambiguity and Language Model Evaluation
- Blog: A Study on Accessing Linguistic Information in Pre-Trained Language Models by Using Prompts
- Blog: Prompting is not a substitute for probability measurements in large language models
- Blog: Knowledge Conflicts for LLMs: A Survey
- Blog: JailNewsBench: Multi-Lingual and Regional Benchmark for Fake News Generation under Jailbreak Attacks
- Blog: Insights into LLM Long-Context Failures: When Transformers Know but Don't Tell
- Blog: Reasoning as State Transition: A Representational Analysis of Reasoning Evolution in Large Language Models
- Blog: Trick or Neat: Adversarial Ambiguity and Language Model Evaluation
- Blog: Constructions Are So Difficult That Even Large Language Models Get Them Right for the Wrong Reasons
- Blog: Knowledge of Pretrained Language Models on Surface Information of Tokens
- Blog: Can LLMs subtract numbers?
- Blog: Supervised and Unsupervised Probing of Shortcut Learning: Case Study on the Emergence and Evolution of Syntactic Heuristics in BERT
- Blog: KG-FPQ: Evaluating Factuality Hallucination in LLMs with Knowledge Graph-based False Premise Questions
- Blog: Can LLMs Ground when they (Don't) Know: A Study on Direct and Loaded Political Questions
- Blog: Inference-Time Intervention: Eliciting Truthful Answers from a Language Model
- Blog: "No, they did not": Dialogue response dynamics in pre-trained language models
- Blog: Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions
- Blog: Are LLMs Really Not Knowledgeable? Mining the Submerged Knowledge in LLMs' Memory
- Blog: Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions
- Blog: Say What You Mean! Large Language Models Speak Too Positively about Negative Commonsense Knowledge
- Blog: The Geometry of Prompting: Unveiling Distinct Mechanisms of Task Adaptation in Language Models
- Blog: Large Language Models as Neurolinguistic Subjects: Discrepancy between Performance and Competence
- Blog: Token-Level Logits Matter: A Closer Look at Speech Foundation Models for Ambiguous Emotion Recognition
- Blog: LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations
- Blog: Are LLMs Really Not Knowledgable? Mining the Submerged Knowledge in LLMs' Memory
- Blog: Truth Forest: Toward Multi-Scale Truthfulness in Large Language Models through Intervention without Tuning
- Blog: Analyzing LLMs' Knowledge Boundary Cognition Across Languages Through the Lens of Internal Representations
- Blog: Traffic Light or Light Traffic? Investigating Phrasal Semantics in Large Language Models
- Blog: Recovering Event Probabilities from Large Language Model Embeddings via Axiomatic Constraints
- Blog: Emergent Response Planning in LLMs
- Blog: Learning to Trust Your Feelings: Leveraging Self-awareness in LLMs for Hallucination Mitigation
- Blog: Response Uncertainty and Probe Modeling: Two Sides of the Same Coin in LLM Interpretability?
- Blog: What Do Large Language Models Know About Opinions?
- Blog: Constructions Are So Difficult That Even Large Language Models Get Them Right for the Wrong Reasons
- Blog: Unsupervised Contrast-Consistent Ranking with Language Models
- Blog: A Survey on the Honesty of Large Language Models
- Blog: Improving Diversity of Demographic Representation in Large Language Models via Collective-Critiques and Self-Voting
- Blog: Improving Preference Extraction In LLMs By Identifying Latent Knowledge Through Classifying Probes
- Blog: Emergent Response Planning in LLM
- Blog: Cat, Rat, Meow: On the Alignment of Language Model and Human Term-Similarity Judgments
- Blog: LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations
- Blog: Efficient Latent Semantic Clustering for Scaling Test-Time Computation of LLMs
- Blog: ControlLM: Crafting Diverse Personalities for Language Models
- Blog: Adaptive Activation Steering: A Tuning-Free LLM Truthfulness Improvement Method for Diverse Hallucinations Categories
- Blog: Answering the Unanswerable Is to Err Knowingly: Analyzing and Mitigating Abstention Failures in Large Reasoning Models
- Blog: HACK: Hallucinations Along Certainty and Knowledge Axes
- Blog: Can A Base LLM Verify Its Own Math? A Pre-Registered Discriminator-Generator Asymmetry Test On AIME And Four Corrective Probes
- Blog: Unsupervised Contrast-Consistent Ranking with Language Models
- Blog: Large Language Models as Neurolinguistic Subjects: Identifying Internal Representations for Form and Meaning
- Blog: Test-Time Matching: Unlocking Compositional Reasoning in Multimodal Models
- Blog: In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation
- Blog: Probing LLMs for Multilingual Discourse Generalization Through a Unified Label Set
- Blog: Depth-Wise Activation Steering for Honest Language Models
- Blog: Controllable Text Generation with Language Constraints
Showing 60 of 199 papers.
History & citation
Current · Permanent link
- This direction split from Aligning Internal Model Knowledge with External Token Generation (87% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_internal_external_knowledge_gap_dd2674d9,
title = {internal-external knowledge gap},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/internal-external-knowledge-gap/rdr_dd2674d9610a4097a848b4afd093d155},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_internal_external_knowledge_gap_dd2674d9_v1,
title = {internal-external knowledge gap},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/internal-external-knowledge-gap/rdr_dd2674d9610a4097a848b4afd093d155/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}