Search Results for author:
Found 37 papers, 13 papers with code
If an LLM Were a Character, Would It Know Its Own Story? Evaluating Lifelong Learning in LLMs
However, during multi-turn, multi-agent interactions, LLMs begin to exhibit consistent, character-like behaviors, hinting at a form of emergent lifelong learning.
SeniorTalk: A Chinese Conversation Dataset with Rich Annotations for Super-Aged Seniors
While voice technologies increasingly serve aging populations, current systems exhibit significant performance gaps due to inadequate training data capturing elderly-specific vocal characteristics like presbyphonia and dialectal variations.
Position-Aware Depth Decay Decoding ($D^3$): Boosting Large Language Model Inference Efficiency
Experiments on large language models (\ie the Llama) with $7 \sim 70$ billion parameters show that $D^3$ can achieve an average 1. 5x speedup compared with the full-inference pipeline while maintaining comparable performance with nearly no performance drop ($<1\%$) on the GSM8K and BBH benchmarks.
CS-Dialogue: A 104-Hour Dataset of Spontaneous Mandarin-English Code-Switching Dialogues for Speech Recognition
Code-switching (CS), the alternation between two or more languages within a single conversation, presents significant challenges for automatic speech recognition (ASR) systems.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Few-Shot Learner Generalizes Across AI-Generated Image Detection
Current fake image detectors trained on large synthetic image datasets perform satisfactorily on limited studied generative models.
Knowledge Editing with Dynamic Knowledge Graphs for Multi-Hop Question Answering
Multi-hop question answering (MHQA) poses a significant challenge for large language models (LLMs) due to the extensive knowledge demands involved.
Commonsense Knowledge Editing Based on Free-Text in LLMs
Knowledge editing technology is crucial for maintaining the accuracy and timeliness of large language models (LLMs) .
Reasons and Solutions for the Decline in Model Performance after Editing
In order to investigate the reasons for the performance decline of the edited model and optimize the editing method, this work explores the underlying reasons from both data and model perspectives.
Sketch: A Toolkit for Streamlining LLM Operations
Sketch comprises the following components: (1) a suite of task description schemas and prompt templates encompassing various NLP tasks; (2) a user-friendly, interactive process for building structured output LLM services tailored to various NLP tasks; (3) an open-source dataset for output format control, along with tools for dataset construction; and (4) an open-source model based on LLaMA3-8B-Instruct that adeptly comprehends and adheres to output formatting instructions.
Open-domain Implicit Format Control for Large Language Model Generation
Controlling the format of outputs generated by large language models (LLMs) is a critical functionality in various applications.
52B to 1T: Lessons Learned via Tele-FLM Series
Large Language Models (LLMs) represent a significant stride toward Artificial General Intelligence.
Improving Zero-shot LLM Re-Ranker with Risk Minimization
In the Retrieval-Augmented Generation (RAG) system, advanced Large Language Models (LLMs) have emerged as effective Query Likelihood Models (QLMs) in an unsupervised way, which re-rank documents based on the probability of generating the query given the content of a document.
SpikeLM: Towards General Spike-Driven Language Modeling via Elastic Bi-Spiking Mechanisms
We plug this elastic bi-spiking mechanism in language modeling, named SpikeLM.
Multimodal Reasoning with Multimodal Knowledge Graph
Multimodal reasoning with large language models (LLMs) often suffers from hallucinations and the presence of deficient or outdated knowledge within LLMs.
Tele-FLM Technical Report
Large language models (LLMs) have showcased profound capabilities in language understanding and generation, facilitating a wide array of applications.
Not All Layers of LLMs Are Necessary During Inference
That is, not all layers of LLMs are necessary during inference.
Discerning and Resolving Knowledge Conflicts through Adaptive Decoding with Contextual Information-Entropy Constraint
Large language models internalize enormous parametric knowledge during pre-training.
Spectral-Based Graph Neural Networks for Complementary Item Recommendation
In this study, we present a novel approach called Spectral-based Complementary Graph Neural Networks (SComGNN) that utilizes the spectral properties of complementary item graphs.
BiPFT: Binary Pre-trained Foundation Transformer with Low-rank Estimation of Binarization Residual Polynomials
Specifically, we first analyze the binarization error in self-attention operations and derive the polynomials of binarization error.
Quantifying and Attributing the Hallucination of Large Language Models via Association Analysis
Although demonstrating superb performance on various NLP tasks, large language models (LLMs) still suffer from the hallucination problem, which threatens the reliability of LLMs.
FLM-101B: An Open LLM and How to Train It with $100K Budget
Large language models (LLMs) are considered important approaches towards foundational machine intelligence, achieving remarkable success in Natural Language Processing and multimodal tasks, among others.
Rethinking Document-Level Relation Extraction: A Reality Check
Recently, numerous efforts have continued to push up performance boundaries of document-level relation extraction (DocRE) and have claimed significant progress in DocRE.
Masked Structural Growth for 2x Faster Language Model Pre-training
In terms of growth schedule, the impact of each single dimension on a schedule's efficiency is under-explored by existing work.
FreeLM: Fine-Tuning-Free Language Model
FreeLM outperforms large models e. g., GPT-3 and InstructGPT, on a range of language understanding tasks in experiments.
NetGPT: Generative Pretrained Transformer for Network Traffic
Pretrained models for network traffic can utilize large-scale raw data to learn the essential characteristics of network traffic, and generate distinguishable results for input traffic without considering specific downstream tasks.
nanoLM: an Affordable LLM Pre-training Benchmark via Accurate Loss Prediction across Scales
With around 14% of the one-time pre-training cost, we can accurately forecast the loss for models up to 52B.
DialogPaint: A Dialog-based Image Editing Model
We introduce DialogPaint, a novel framework that bridges conversational interactions with image editing, enabling users to modify images through natural dialogue.
GCRE-GPT: A Generative Model for Comparative Relation Extraction
Given comparative text, comparative relation extraction aims to extract two targets (\eg two cameras) in comparison and the aspect they are compared for (\eg image quality).
PoKE: Prior Knowledge Enhanced Emotional Support Conversation with Latent Variable
Further experiments prove that abundant prior knowledge is conducive to high-quality emotional support, and a well-learned latent variable is critical to the diversity of generations.
Perplexity from PLM Is Unreliable for Evaluating Text Quality
Recently, amounts of works utilize perplexity~(PPL) to evaluate the quality of the generated text.
CofeNet: Context and Former-Label Enhanced Net for Complicated Quotation Extraction
CofeNet is able to extract complicated quotations with components of variable lengths and complicated structures.
Chat-Capsule: A Hierarchical Capsule for Dialog-level Emotion Analysis
These models hence are not optimized for dialog-level emotion detection, i. e. to predict the emotion category of a dialog as a whole.
Aspect-based Sentiment Analysis through EDU-level Attentions
A sentence may express sentiments on multiple aspects.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+1
A Dual-Channel Framework for Sarcasm Recognition by Detecting Sentiment Conflict
Based on this dual-channel framework, we design the Dual-Channel Network~(DC-Net) to recognize sentiment conflict.
Keyphrase Extraction with Span-based Feature Representations
In addition, with the help of tokens, our model is able to extract overlapped keyphrases.
Sentiment Analysis by Capsules
Based on capsule representation, the probability module computes the capsule’s state probability.
Ranked #6 on
Sentiment Analysis
on MR
