No article text was recorded for this version.
alignment-induced knowledge degradation
Version 1 of 119 papers33 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Towards Practical and Knowledgeable LLMs for a Multilingual World: A Thesis Proposal
- Blog: Towards Reliable Latent Knowledge Estimation in LLMs: Zero-Prompt Many-Shot Based Factual Knowledge Extraction
- Blog: Statistical Knowledge Assessment for Large Language Models
- Blog: Unpacking Large Language Models with Conceptual Consistency
- Blog: Evaluating Hallucinations in Chinese Large Language Models
- Blog: A + B: A General Generator-Reader Framework for Optimizing LLMs to Unleash Synergy Potential
- Blog: Style Outweighs Substance: Failure Modes of LLM Judges in Alignment Benchmarking
- Blog: Chinese SimpleQA: A Chinese Factuality Evaluation for Large Language Models
- Blog: What Matters in Memorizing and Recalling Facts? Multifaceted Benchmarks for Knowledge Probing in Language Models
- Blog: HumanRankEval: Automatic Evaluation of LMs as Conversational Assistants
- Blog: Fact or Facsimile? Evaluating the Factual Robustness of Modern Retrievers
- Blog: Do Large Language Models Know Folktales? A Case Study of Yokai in Japanese Folktales
- Blog: Weak-to-Strong Preference Optimization: Stealing Reward from Weak Aligned Model
- Blog: CareBot: A Pioneering Full-Process Open-Source Medical Language Model
- Blog: Open-source Large Language Models are Strong Zero-shot Query Likelihood Models for Document Ranking
- Blog: Reinforcement Learning Improves Traversal of Hierarchical Knowledge in LLMs
- Blog: Don't Throw Away Your Pretrained Model
- Blog: A Closer Look at the Limitations of Instruction Tuning
- Blog: LoRAMoE: Alleviating World Knowledge Forgetting in Large Language Models via MoE-Style Plugin
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_alignment_induced_knowledge_degradation_a2c8059f,
title = {alignment-induced knowledge degradation},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/alignment-induced-knowledge-degradation/rdr_a2c8059fe0a4458a84a4477a5582b9b5},
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_alignment_induced_knowledge_degradation_a2c8059f_v1,
title = {alignment-induced knowledge degradation},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/alignment-induced-knowledge-degradation/rdr_a2c8059fe0a4458a84a4477a5582b9b5/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}