Cognitive

Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMs	2025 COLM
Language Models Are Capable of Metacognitive Monitoring and Control of Their Internal Activations	2025, url
On the Same Wavelength? Evaluating Pragmatic Reasoning in Language Models across Broad Concepts	Tenenbaum, 2025 url

Steering

Activation Steering in Generative Settings via Contrastive Causal Mediation Analysis

Knowledge Conflict

Conflict-Aware Soft Prompting for Retrieval-Augmented Generation (EMNLP 2025)	url
KCR: Resolving Long-Context Knowledge Conflicts via Reasoning in LLMs	url
An Unlearning-based Approach to Conflict-free Model Editing
Resolving Knowledge Conflicts in Large Language Models
Can I understand what I create? Self-Knowledge Evaluation of Large Language Models
Taming Knowledge Conflicts in Language Models (ICML 2025)

Neuron Interpretation for LLM

Unveiling the Pitfalls of Knowledge Editing for Large Language Models	(ICLR 2024)
The Origins of Representation Manifolds in Large Language Models	(2025)

LLM Study

|Fluid Language Model Benchmarking | COLM 2025 | |Language Self-Play For Data-Free Training | (2025) |

NMR Logic

An Efficient Reasoner for Description Logics of Typicality and Rational Closure?	2017
Generics and Default Reasoning in Large Language Models	2025
Know your exceptions	2024

LLM Study

Compute as Teacher: Turning Inference Compute Into Reference-Free Supervision
Scaling Agents via Continual Pre-training
DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning
AuPair: Golden Example Pairs for Code Repair (ICML 2025) Self-repair, Fix Quality Matrix, Submodular selection, In-context examples (AuPairs)	url