Can Retriever-Augmented Language Models Reason? The Blame Game Between the Retriever and the Language Model
Paper
• 2212.09146 • Published
• 3
emlnp 2023 tbd
-
-
RaLLe: A Framework for Developing and Evaluating Retrieval-Augmented Large Language Models
Paper • 2308.10633 • Published • 1 -
MemeCap: A Dataset for Captioning and Interpreting Memes
Paper • 2305.13703 • Published -
Contrastive Learning for Inference in Dialogue
Paper • 2310.12467 • Published -
Multi-level Adaptive Contrastive Learning for Knowledge Internalization in Dialogue Generation
Paper • 2310.08943 • Published -
Fine-grained Conversational Decoding via Isotropic and Proximal Search
Paper • 2310.08130 • Published -
Bridging the Gap: A Survey on Integrating (Human) Feedback for Natural Language Generation
Paper • 2305.00955 • Published -
Air-Decoding: Attribute Distribution Reconstruction for Decoding-Time Controllable Text Generation
Paper • 2310.14892 • Published • 1 -
KNN-LM Does Not Improve Open-ended Text Generation
Paper • 2305.14625 • Published • 1 -
Symbol tuning improves in-context learning in language models
Paper • 2305.08298 • Published • 3 -
Transcending Scaling Laws with 0.1% Extra Compute
Paper • 2210.11399 • Published -
Unveiling the Implicit Toxicity in Large Language Models
Paper • 2311.17391 • Published -
Adapting Language Models to Compress Contexts
Paper • 2305.14788 • Published • 1 -
Failures Pave the Way: Enhancing Large Language Models through Tuning-free Rule Accumulation
Paper • 2310.15746 • Published -
Data Similarity is Not Enough to Explain Language Model Performance
Paper • 2311.09006 • Published -
Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback
Paper • 2305.14975 • Published • 2 -
MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions
Paper • 2305.14795 • Published -
Model-tuning Via Prompts Makes NLP Models Adversarially Robust
Paper • 2303.07320 • Published -
Look-back Decoding for Open-Ended Text Generation
Paper • 2305.13477 • Published -
Reasoning with Language Model is Planning with World Model
Paper • 2305.14992 • Published • 4 -
Skill-Based Few-Shot Selection for In-Context Learning
Paper • 2305.14210 • Published -
MoT: Memory-of-Thought Enables ChatGPT to Self-Improve
Paper • 2305.05181 • Published -
How Do Large Language Models Capture the Ever-changing World Knowledge? A Review of Recent Advances
Paper • 2310.07343 • Published -
Explore-Instruct: Enhancing Domain-Specific Instruction Coverage through Active Exploration
Paper • 2310.09168 • Published • 2 -
Editing Large Language Models: Problems, Methods, and Opportunities
Paper • 2305.13172 • Published • 1 -
Shall We Pretrain Autoregressive Language Models with Retrieval? A Comprehensive Study
Paper • 2304.06762 • Published • 1 -
Active Instruction Tuning: Improving Cross-Task Generalization by Training on Prompt Sensitive Tasks
Paper • 2311.00288 • Published -
Mind the Gap Between Conversations for Improved Long-Term Dialogue Generation
Paper • 2310.15415 • Published -
Data Factors for Better Compositional Generalization
Paper • 2311.04420 • Published -
Inverse scaling can become U-shaped
Paper • 2211.02011 • Published -
Composable Text Controls in Latent Space with ODEs
Paper • 2208.00638 • Published -
Can We Edit Factual Knowledge by In-Context Learning?
Paper • 2305.12740 • Published -
Compressing Context to Enhance Inference Efficiency of Large Language Models
Paper • 2310.06201 • Published -
Context Compression for Auto-regressive Transformers with Sentinel Tokens
Paper • 2310.08152 • Published • 1 -
Cognitive Dissonance: Why Do Language Model Outputs Disagree with Internal Representations of Truthfulness?
Paper • 2312.03729 • Published -
Characterizing Mechanisms for Factual Recall in Language Models
Paper • 2310.15910 • Published -
Auto-Instruct: Automatic Instruction Generation and Ranking for Black-Box Language Models
Paper • 2310.13127 • Published • 12 -
DecipherPref: Analyzing Influential Factors in Human Preference Judgments via GPT-4
Paper • 2305.14702 • Published • 1 -
Revisiting Entropy Rate Constancy in Text
Paper • 2305.12084 • Published -
Subspace Chronicles: How Linguistic Information Emerges, Shifts and Interacts during Language Model Training
Paper • 2310.16484 • Published -
Language Models with Rationality
Paper • 2305.14250 • Published -
An Attribution Method for Siamese Encoders
Paper • 2310.05703 • Published -
Universal Self-Adaptive Prompting
Paper • 2305.14926 • Published -
Let's Synthesize Step by Step: Iterative Dataset Synthesis with Large Language Models by Extrapolating Errors from Small Models
Paper • 2310.13671 • Published • 19 -
Interpreting Embedding Spaces by Conceptualization
Paper • 2209.00445 • Published -
Norm of Word Embedding Encodes Information Gain
Paper • 2212.09663 • Published -
Measuring Attribution in Natural Language Generation Models
Paper • 2112.12870 • Published -
Statistical Depth for Ranking and Characterizing Transformer-Based Text Embeddings
Paper • 2310.15010 • Published -
Bridging Information-Theoretic and Geometric Compression in Language Models
Paper • 2310.13620 • Published -
Do LLMs Understand Social Knowledge? Evaluating the Sociability of Large Language Models with SocKET Benchmark
Paper • 2305.14938 • Published -
Goal-Driven Explainable Clustering via Language Descriptions
Paper • 2305.13749 • Published -
Ditto: A Simple and Efficient Approach to Improve Sentence Embeddings
Paper • 2305.10786 • Published -
Analyzing Norm Violations in Live-Stream Chat
Paper • 2305.10731 • Published -
Lion: Adversarial Distillation of Closed-Source Large Language Model
Paper • 2305.12870 • Published -
To Build Our Future, We Must Know Our Past: Contextualizing Paradigm Shifts in Natural Language Processing
Paper • 2310.07715 • Published -
Large Language Models: The Need for Nuance in Current Debates and a Pragmatic Perspective on Understanding
Paper • 2310.19671 • Published -
FreeAL: Towards Human-Free Active Learning in the Era of Large Language Models
Paper • 2311.15614 • Published