Search Results for author:
Found 11 papers, 5 papers with code
Instruction Embedding: Latent Representations of Instructions Towards Task Identification
In this work, we introduce a new concept, instruction embedding, and construct Instruction Embedding Benchmark (IEB) for its training and evaluation.
Focused Large Language Models are Stable Many-Shot Learners
With the increase in available context length of LLMs, recent experiments have shown that the performance of ICL does not necessarily scale well in many-shot (demonstration) settings.
Poor-Supervised Evaluation for SuperLLM via Mutual Consistency
To alleviate the insufficiencies of the conditions in reality, we further introduce an algorithm that treats humans (when available) and the models under evaluation as reference models, alternately conducting model weights calibration and filtering during E-step and M-step.
Make Every Penny Count: Difficulty-Adaptive Self-Consistency for Cost-Efficient Reasoning
To demonstrate the effectiveness of DSC, we conduct extensive experiments on three popular categories of reasoning tasks: arithmetic, commonsense and symbolic reasoning on six benchmarks.
CogLM: Tracking Cognitive Development of Large Language Models
As Large Language Models (LLMs) have recently shown remarkable abilities across a wide variety of tasks, we are curious about the cognitive levels of current LLMs: to what extent they have developed and how this development has been achieved.
Integrate the Essence and Eliminate the Dross: Fine-Grained Self-Consistency for Free-Form Language Generation
These methods, however, face limitations due to their inability to fully utilize the nuanced consensus knowledge present within multiple candidate samples, often resulting in suboptimal outputs.
Generative Dense Retrieval: Memory Can Be a Burden
Memorizing-free matching mechanism from Dense Retrieval (DR) is then introduced to conduct fine-grained intra-cluster matching from clusters to relevant documents.
BatchEval: Towards Human-like Text Evaluation
Significant progress has been made in automatic text evaluation with the introduction of large language models (LLMs) as evaluators.
Turning Dust into Gold: Distilling Complex Reasoning Capabilities from LLMs by Leveraging Negative Data
In this work, we illustrate the merit of negative data and propose a model specialization framework to distill LLMs with negative samples besides positive ones.
Boosting Entity-aware Image Captioning with Multi-modal Knowledge Graph
Entity-aware image captioning aims to describe named entities and events related to the image by utilizing the background knowledge in the associated article.
