conftrace_

hidden state

113 papers

Explore in graph

Co-occurring keywords

recurrent neural network (1790) large language model (13587) language model (4599) representation learning (6206) attention mechanism (4001) hallucination detection (530) hidden state analysis (13) state space model (390) in-context learning (1405) transformer architecture (1560)

Papers

Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation AAAI 2026
Suppressing Final Layer Hidden State Jumps in Transformer Pretraining EACL 2026
SlimInfer: Accelerating Long-Context LLM Inference via Dynamic Token Pruning AAAI 2026
Your Reasoning Model is Secretly a Reward Model - Optimization-Free Verification from Experience ACL 2026
A Unified View on Emotion Representation in Large Language Models EACL 2026
Look Before You Leap: A Lookahead Reasoning Quality Gate for Speculative Decoding EACL 2026
LLMs Know More About Numbers than They Can Say EACL 2026
ESMC: MLLM-Based Embedding Selection for Explainable Multiple Clustering AAAI 2026
Learning Uncertainty from Sequential Internal Dispersion in Large Language Models ACL 2026
Activation-Guided Local Editing for Jailbreaking Attacks ACL 2026
Mitigate Position Bias in LLMs via Scaling a Single Hidden States Channel ACL 2025
Activation Steering Decoding: Mitigating Hallucination in Large Vision-Language Models through Bidirectional Hidden State Intervention ACL 2025
Token-based Decision Criteria Are Suboptimal in In-context Learning NAACL 2025
DenseSSM: State Space Models with Dense Hidden Connection for Efficient Large Language Models NAACL 2025
Evaluation of LLMs-based Hidden States as Author Representations for Psychological Human-Centered NLP Tasks NAACL 2025
LAMB: A Training-Free Method to Enhance the Long-Context Understanding of SSMs via Attention-Guided Token Filtering ACL 2025
Bold Claims or Self-Doubt? Factuality Hallucination Type Detection via Belief State EMNLP 2025
Defending against Indirect Prompt Injection by Instruction Detection EMNLP 2025
Simple Factuality Probes Detect Hallucinations in Long-Form Natural Language Generation EMNLP 2025
HiddenDetect: Detecting Jailbreak Attacks against Multimodal Large Language Models via Monitoring Hidden States ACL 2025
Characterizing Mamba’s Selective Memory using Auto-Encoders IJCNLP 2025
Linear Steerability in Language Models: When It Emerges and How It Evolves EMNLP 2025
ICR Probe: Tracking Hidden State Dynamics for Reliable Hallucination Detection in LLMs ACL 2025
Characterizing Mamba’s Selective Memory using Auto-Encoders AACL 2025
Back Attention: Understanding and Enhancing Multi-Hop Reasoning in Large Language Models EMNLP 2025