Search Results for author:
Found 45 papers, 12 papers with code
Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs
The remarkable performance of models like the OpenAI o1 can be attributed to their ability to emulate human-like long-time thinking during inference.
HUNYUANPROVER: A Scalable Data Synthesis Framework and Guided Tree Search for Automated Theorem Proving
We introduce HunyuanProver, an language model finetuned from the Hunyuan 7B for interactive automatic theorem proving with LEAN4.
Teaching LLMs to Refine with Tools
We propose CaP, a novel approach that uses external tools to refine chain-of-thought (CoT) responses generated by the same or other LLMs.
Low-Bit Quantization Favors Undertrained LLMs: Scaling Laws for Quantized LLMs with 100T Training Tokens
To gain deeper insights into this trend, we study over 1500 quantized LLM checkpoints of various sizes and at different training levels (undertrained or fully trained) in a controlled setting, deriving scaling laws for understanding the relationship between QiD and factors such as the number of training tokens, model size and bit width.
Towards Self-Improvement of LLMs via MCTS: Leveraging Stepwise Knowledge with Curriculum Preference Learning
Monte Carlo Tree Search (MCTS) has recently emerged as a powerful technique for enhancing the reasoning capabilities of LLMs.
DOTS: Learning to Reason Dynamically in LLMs via Optimal Reasoning Trajectories Search
In this paper, we propose DOTS, an approach enabling LLMs to reason dynamically via optimal reasoning trajectory search, tailored to the specific characteristics of each question and the inherent capability of the task-solving LLM.
HDFlow: Enhancing LLM Complex Problem-Solving with Hybrid Thinking and Dynamic Workflows
Despite recent advancements in large language models (LLMs), their performance on complex reasoning problems requiring multi-step thinking and combining various skills is still limited.
SIaM: Self-Improving Code-Assisted Mathematical Reasoning of Large Language Models
There is a growing trend of teaching large language models (LLMs) to solve mathematical problems through coding.
Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret Learning
Specifically, we formulate the problem as a two-player game and propose a novel online algorithm, iterative Nash policy optimization (INPO).
LiteSearch: Efficacious Tree Search for LLM
Recent research suggests that tree search algorithms (e. g. Monte Carlo Tree Search) can dramatically boost LLM performance on complex mathematical reasoning tasks.
Scaling Synthetic Data Creation with 1,000,000,000 Personas
We propose a novel persona-driven data synthesis methodology that leverages various perspectives within a large language model (LLM) to create diverse synthetic data.
Self-Tuning: Instructing LLMs to Effectively Acquire New Knowledge through Self-Teaching
Motivated by the remarkable success of the Feynman Technique in efficient human learning, we introduce Self-Tuning, a learning framework aimed at improving an LLM's ability to effectively acquire new knowledge from raw documents through self-teaching.
Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing
Despite the impressive capabilities of Large Language Models (LLMs) on various tasks, they still struggle with scenarios that involves complex reasoning and planning.
Ranked #1 on
GSM8K
on GSM8K
Entropy Guided Extrapolative Decoding to Improve Factuality in Large Language Models
Current state-of-the-art approaches refine decoding by contrasting early-exit distributions from a lower layer with the final layer to exploit information related to factuality within the model forward procedure.
Self-Consistency Boosts Calibration for Math Reasoning
Calibration, which establishes the correlation between accuracy and model confidence, is important for LLM development.
A Knowledge Plug-and-Play Test Bed for Open-domain Dialogue Generation
In this paper, we present a high-quality benchmark named multi-source Wizard of Wikipedia (Ms. WoW) for evaluating multi-source dialogue knowledge selection and response generation.
Collaborative decoding of critical tokens for boosting factuality of large language models
The most common training pipeline for large language models includes pretraining, finetuning and aligning phases, with their respective resulting models, such as the pretrained model and the finetuned model.
Fine-Grained Self-Endorsement Improves Factuality and Reasoning
Experiments on Biographies show that our method can effectively improve the factuality of generations with simple and intuitive prompts across different scales of LLMs.
Self-Alignment for Factuality: Mitigating Hallucinations in LLMs via Self-Evaluation
Despite showing increasingly human-like abilities, large language models (LLMs) often struggle with factual inaccuracies, i. e. "hallucinations", even when they hold relevant knowledge.
Inconsistent dialogue responses and how to recover from them
One critical issue for chat systems is to stay consistent about preferences, opinions, beliefs and facts of itself, which has been shown a difficult problem.
The Trickle-down Impact of Reward (In-)consistency on RLHF
We propose Contrast Instructions -- a benchmarking strategy for the consistency of RM.
Stabilizing RLHF through Advantage Model and Selective Rehearsal
Large Language Models (LLMs) have revolutionized natural language processing, yet aligning these models with human values and preferences using RLHF remains a significant challenge.
Search-Engine-augmented Dialogue Response Generation with Cheaply Supervised Query Production
We propose a dialogue model that can access the vast and dynamic information from any search engine for response generation.
Friend-training: Learning from Models of Different but Related Tasks
Current self-training methods such as standard self-training, co-training, tri-training, and others often focus on improving model performance on a single task, utilizing differences in input features, model architectures, and training processes.
Discover, Explanation, Improvement: An Automatic Slice Detection Framework for Natural Language Processing
Pretrained natural language processing (NLP) models have achieved high overall performance, but they still make systematic errors.
Learning a Grammar Inducer from Massive Uncurated Instructional Videos
While previous work focuses on building systems for inducing grammars on text that are well-aligned with video content, we investigate the scenario, in which text and video are only in loose correspondence.
Towards Generalized Models for Task-oriented Dialogue Modeling on Spoken Conversations
Building robust and general dialogue models for spoken conversations is challenging due to the gap in distributions of spoken and written data.
Fast-R2D2: A Pretrained Recursive Neural Network based on Pruned CKY for Grammar Induction and Text Representation
We propose to use a top-down parser as a model-based pruning method, which also enables parallel encoding during inference.
DP-FP: Differentially Private Forward Propagation for Large Models
Our DP-FP employs novel (1) representation clipping followed by noise addition in the forward propagation stage, as well as (2) micro-batch construction via subsampling to achieve DP amplification and reduce noise power to $1/M$, where $M$ is the number of micro-batch in a step.
A Dialogue-based Information Extraction System for Medical Insurance Assessment
In the Chinese medical insurance industry, the assessor's role is essential and requires significant efforts to converse with the claimant.
R2D2: Recursive Transformer based on Differentiable Tree for Interpretable Hierarchical Language Modeling
Human language understanding operates at multiple levels of granularity (e. g., words, phrases, and sentences) with increasing levels of abstraction that can be hierarchically combined.
Multi-Perspective Context Matching for Machine Comprehension
Based on this dataset, we propose a Multi-Perspective Context Matching (MPCM) model, which is an end-to-end system that directly predicts the answer beginning and ending points in a passage.
Ranked #3 on
Open-Domain Question Answering
on SQuAD1.1
Temporal Attention Model for Neural Machine Translation
Attention-based Neural Machine Translation (NMT) models suffer from attention deficiency issues as has been observed in recent research.
Supervised Attentions for Neural Machine Translation
We simply compute the distance between the machine attentions and the "true" alignments, and minimize this cost in the training procedure.
Sense Embedding Learning for Word Sense Induction
In the training stage, our method induces several sense centroids (embedding) for each polysemous word.
Ranked #4 on
Word Sense Induction
on SemEval 2010 WSI
Coverage Embedding Models for Neural Machine Translation
In this paper, we enhance the attention-based neural machine translation (NMT) by adding explicit coverage embedding models to alleviate issues of repeating and dropping translations in NMT.
Vocabulary Manipulation for Neural Machine Translation
Our method simply takes into account the translation options of each word or phrase in the source sentence, and picks a very small target vocabulary for each sentence based on a word-to-word translation model or a bilingual phrase library learned from a traditional machine translation model.
Sentence Similarity Learning by Lexical Decomposition and Composition
Most conventional sentence similarity methods only focus on similar parts of two input sentences, and simply ignore the dissimilar parts, which usually give us some clues and semantic meanings about the sentences.
Ranked #13 on
Question Answering
on WikiQA
Semi-supervised Clustering for Short Text via Deep Representation Learning
In this work, we propose a semi-supervised method for short text clustering, where we represent texts as distributed vectors with neural networks, and use a small amount of labeled data to specify our intention for clustering.
