Search Results for author:
Found 31 papers, 19 papers with code
Decoding on Graphs: Faithful and Sound Reasoning on Knowledge Graphs through Generation of Well-Formed Chains
We argue that this concept can serve as a principle for making faithful and sound reasoning for KGQA.
Quantifying Generalization Complexity for Large Language Models
Scylla disentangles generalization from memorization via assessing model performance on both in-distribution (ID) and out-of-distribution (OOD) data through 20 tasks across 5 levels of complexity.
Addition is All You Need for Energy-efficient Language Models
The new algorithm costs significantly less computation resource than 8-bit floating point multiplication but achieves higher precision.
Training Task Experts through Retrieval Based Distillation
One of the most reliable ways to create deployable models for specialized tasks is to obtain an adequate amount of high-quality task-specific data.
Self-MoE: Towards Compositional Large Language Models with Self-Specialized Experts
Our findings highlight the critical role of modularity, the applicability of Self-MoE to multiple base LLMs, and the potential of self-improvement in achieving efficient, scalable, and adaptable systems.
Adaptive Query Rewriting: Aligning Rewriters through Marginal Probability of Conversational Answers
A novel approach is then proposed to assess retriever's preference for these candidates by the probability of answers conditioned on the conversational query by marginalizing the Top-$K$ passages.
THREAD: Thinking Deeper with Recursive Spawning
We apply THREAD in the settings of LLM task solving and question answering, where the dynamic threading allows the model to recursively decompose the given task or question into progressively simpler sub-problems that can be solved by separate child threads.
RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation
To this end, we propose learning to Refine Query for Retrieval Augmented Generation (RQ-RAG) in this paper, endeavoring to enhance the model by equipping it with capabilities for explicit rewriting, decomposition, and disambiguation.
HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding
While large vision-language models (LVLMs) have demonstrated impressive capabilities in interpreting multi-modal contexts, they invariably suffer from object hallucinations (OH).
Self-Specialization: Uncovering Latent Expertise within Large Language Models
Recent works have demonstrated the effectiveness of self-alignment in which a large language model is aligned to follow general instructions using instructional data generated from the model itself starting from a handful of human-written seeds.
Joint Audio and Speech Understanding
Humans are surrounded by audio signals that include both speech and non-speech sounds.
Natural Language Embedded Programs for Hybrid Language Symbolic Reasoning
How can we perform computations over natural language representations to solve tasks that require symbolic and numeric reasoning?
DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models
Despite their impressive capabilities, large language models (LLMs) are prone to hallucinations, i. e., generating content that deviates from facts seen during pretraining.
Entailment as Robust Self-Learner
Experiments on binary and multi-class classification tasks show that SimPLE leads to more robust self-training results, indicating that the self-trained entailment models are more efficient and trustworthy than large language models on language understanding tasks.
Multi-class Classification
Natural Language Understanding
+1
SAIL: Search-Augmented Instruction Learning
Large language models (LLMs) have been significantly improved by instruction fine-tuning, but still lack transparency and the ability to utilize up-to-date knowledge and information.
Listen, Think, and Understand
On the other hand, modern large language models (LLMs) exhibit emerging reasoning ability but they lack audio perception capabilities.
Ranked #3 on
Music Question Answering
on MusicQA
(using extra training data)
Chain of Thought Prompt Tuning in Vision Language Models
Chain of Thought is a simple and effective approximation to human reasoning process and has been proven useful for natural language processing (NLP) tasks.
Interpretable Unified Language Checking
Despite recent concerns about undesirable behaviors generated by large language models (LLMs), including non-factual, biased, and hateful language, we find LLMs are inherent multi-task language checkers based on their latent representations of natural and social knowledge.
Logic Against Bias: Textual Entailment Mitigates Stereotypical Sentence Reasoning
Due to their similarity-based learning objectives, pretrained sentence encoders often internalize stereotypical assumptions that reflect the social biases that exist within their training corpora.
DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings
We propose DiffCSE, an unsupervised contrastive learning framework for learning sentence embeddings.
Ranked #13 on
Semantic Textual Similarity
on STS16
Mitigating Biases in Toxic Language Detection through Invariant Rationalization
Automatic detection of toxic language plays an essential role in protecting social media users, especially minority groups, from verbal abuse.
Meta-learning for downstream aware and agnostic pretraining
Neural network pretraining is gaining attention due to its outstanding performance in natural language processing applications.
Cooperative Self-training of Machine Reading Comprehension
Pretrained language models have significantly improved the performance of downstream language understanding tasks, including extractive question answering, by providing high-quality contextualized word embeddings.
Ranked #1 on
Question Answering
on MRQA out-of-domain
Extractive Question-Answering
Machine Reading Comprehension
+6
Knowledge Grounded Conversational Symptom Detection with Graph Memory Networks
Given a set of explicit symptoms provided by the patient to initiate a dialog for diagnosing, the system is trained to collect implicit symptoms by asking questions, in order to collect more information for making an accurate diagnosis.
Prototypical Q Networks for Automatic Conversational Diagnosis and Few-Shot New Disease Adaption
Experiments showed that the ProtoQN significantly outperformed the baseline DQN model in both supervised and few-shot learning scenarios, and achieves state-of-the-art few-shot learning performances.
Improving Neural Language Models by Segmenting, Attending, and Predicting the Future
In this work, we propose a method that improves language modeling by learning to align the given context and the following phrase.
Ranked #24 on
Language Modelling
on WikiText-103
Language Modeling with Graph Temporal Convolutional Networks
Recently, there have been some attempts to use non-recurrent neural models for language modeling.
Learning Word Representations with Cross-Sentence Dependency for End-to-End Co-reference Resolution
In this work, we present a word embedding model that learns cross-sentence dependency for improving end-to-end co-reference resolution (E2E-CR).
Ranked #22 on
Coreference Resolution
on OntoNotes
Adaptive Bidirectional Backpropagation: Towards Biologically Plausible Error Signal Transmission in Neural Networks
However, it has been argued that this is not biologically plausible because back-propagating error signals with the exact incoming weights are not considered possible in biological neural systems.
DrMAD: Distilling Reverse-Mode Automatic Differentiation for Optimizing Hyperparameters of Deep Neural Networks
The performance of deep neural networks is well-known to be sensitive to the setting of their hyperparameters.
