DSI++: Updating Transformer Memory with New Documents
Paper
• 2212.09744 • Published
• 1
emnlp 2023
-
-
Where to start? Analyzing the potential value of intermediate models
Paper • 2211.00107 • Published -
INSTRUCTSCORE: Explainable Text Generation Evaluation with Finegrained Feedback
Paper • 2305.14282 • Published -
G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment
Paper • 2303.16634 • Published • 3 -
Outlier Dimensions Encode Task-Specific Knowledge
Paper • 2310.17715 • Published • 2 -
Meta-Learning Online Adaptation of Language Models
Paper • 2305.15076 • Published -
Automatic Evaluation of Generative Models with Instruction Tuning
Paper • 2310.20072 • Published -
Unveiling Safety Vulnerabilities of Large Language Models
Paper • 2311.04124 • Published • 9 -
Dynosaur: A Dynamic Growth Paradigm for Instruction-Tuning Data Curation
Paper • 2305.14327 • Published -
Attention Lens: A Tool for Mechanistically Interpreting the Attention Head Information Retrieval Mechanism
Paper • 2310.16270 • Published • 1 -
Prompt-Based Monte-Carlo Tree Search for Goal-Oriented Dialogue Policy Planning
Paper • 2305.13660 • Published -
Conversation Chronicles: Towards Diverse Temporal and Relational Dynamics in Multi-Session Conversations
Paper • 2310.13420 • Published • 2 -
Rigorously Assessing Natural Language Explanations of Neurons
Paper • 2309.10312 • Published -
Memory Injections: Correcting Multi-Hop Reasoning Failures during Inference in Transformer-Based Language Models
Paper • 2309.05605 • Published • 1 -
Identifying and Adapting Transformer-Components Responsible for Gender Bias in an English Language Model
Paper • 2310.12611 • Published -
RECKONING: Reasoning through Dynamic Knowledge Encoding
Paper • 2305.06349 • Published • 1 -
Penalty Decoding: Well Suppress the Self-Reinforcement Effect in Open-Ended Text Generation
Paper • 2310.14971 • Published -
We are what we repeatedly do: Inducing and deploying habitual schemas in persona-based responses
Paper • 2310.06245 • Published • 1 -
Self-Detoxifying Language Models via Toxification Reversal
Paper • 2310.09573 • Published -
SteerLM: Attribute Conditioned SFT as an (User-Steerable) Alternative to RLHF
Paper • 2310.05344 • Published • 1 -
HelpSteer: Multi-attribute Helpfulness Dataset for SteerLM
Paper • 2311.09528 • Published • 2 -
Enhancing Chat Language Models by Scaling High-quality Instructional Conversations
Paper • 2305.14233 • Published • 7 -
LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models
Paper • 2310.05736 • Published • 4 -
LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression
Paper • 2310.06839 • Published • 4 -
InstructRetro: Instruction Tuning post Retrieval-Augmented Pretraining
Paper • 2310.07713 • Published • 3 -
1-PAGER: One Pass Answer Generation and Evidence Retrieval
Paper • 2310.16568 • Published -
Using In-Context Learning to Improve Dialogue Safety
Paper • 2302.00871 • Published • 1 -
Better Together: Enhancing Generative Knowledge Graph Completion with Language Models and Neighborhood Information
Paper • 2311.01326 • Published • 4 -
Goodtriever: Adaptive Toxicity Mitigation with Retrieval-augmented Models
Paper • 2310.07589 • Published -
When are Lemons Purple? The Concept Association Bias of CLIP
Paper • 2212.12043 • Published -
Sequential Monte Carlo Steering of Large Language Models using Probabilistic Programs
Paper • 2306.03081 • Published -
Backpack Language Models
Paper • 2305.16765 • Published • 1