Search Results for author:
Found 34 papers, 26 papers with code
MARGE: Improving Math Reasoning for LLMs with Guided Exploration
These results demonstrate MARGE's effectiveness in enhancing mathematical reasoning capabilities and unlocking the potential of scaling self-generated training data.
WorldPM: Scaling Human Preference Modeling
Motivated by scaling laws in language modeling that demonstrate how test loss scales as a power law with model and dataset sizes, we find that similar laws exist in preference modeling.
AutoLogi: Automated Generation of Logic Puzzles for Evaluating Reasoning Abilities of Large Language Models
While logical reasoning evaluation of Large Language Models (LLMs) has attracted significant attention, existing benchmarks predominantly rely on multiple-choice formats that are vulnerable to random guessing, leading to overestimated performance and substantial performance fluctuations.
Qwen2.5 Technical Report
In addition, for hosted solutions, the proprietary models currently include two mixture-of-experts (MoE) variants: Qwen2. 5-Turbo and Qwen2. 5-Plus, both available from Alibaba Cloud Model Studio.
Ranked #7 on
on GPQA
ProcessBench: Identifying Process Errors in Mathematical Reasoning
We conduct extensive evaluation on ProcessBench, involving two types of models: process reward models (PRMs) and critic models, where for the latter we prompt general language models to critique each solution step by step.
Aligning Large Language Models via Self-Steering Optimization
The key to automated alignment lies in providing learnable and accurate preference signals for preference learning without human annotation.
A Unified View of Delta Parameter Editing in Post-Trained Large-Scale Models
Post-training has emerged as a crucial paradigm for adapting large-scale pre-trained models to various tasks, whose effects are fully reflected by delta parameters (i. e., the disparity between post-trained and pre-trained parameters).
Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement
This RM is then applied to the iterative evolution of data in supervised fine-tuning (SFT).
Ranked #2 on
Math Word Problem Solving
on MATH
(using extra training data)
Qwen2.5-Coder Technical Report
In this report, we introduce the Qwen2. 5-Coder series, a significant upgrade from its predecessor, CodeQwen1. 5.
Towards a Unified View of Preference Learning for Large Language Models: A Survey
Finally, based on our unified perspective, we explore the challenges and future research directions for aligning large language models with human preferences.
Predicting Rewards Alongside Tokens: Non-disruptive Parameter Insertion for Efficient Inference Intervention in Large Language Model
Transformer-based large language models (LLMs) exhibit limitations such as generating unsafe responses, unreliable reasoning, etc.
Qwen2 Technical Report
This report introduces the Qwen2 series, the latest addition to our large language models and large multimodal models.
Ranked #3 on
Arithmetic Reasoning
on GSM8K
(using extra training data)
LLM Critics Help Catch Bugs in Mathematics: Towards a Better Mathematical Verifier with Natural Language Feedback
In recent progress, mathematical verifiers have achieved success in mathematical reasoning tasks by validating the correctness of solutions generated by policy models.
Self-play with Execution Feedback: Improving Instruction-following Capabilities of Large Language Models
AutoIF transforms the validation of instruction-following data quality into code verification, requiring LLMs to generate instructions, the corresponding code to check the correctness of the instruction responses, and unit test samples to verify the code's correctness.
Ranked #1 on
Instruction Following
on IFEval
PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Our experimental evaluations, utilizing the LongBench benchmark, show that PyramidKV matches the performance of models with a full KV cache while retaining only 12% of the KV cache, thus significantly reducing memory usage.
Towards Scalable Automated Alignment of LLMs: A Survey
Alignment is the most critical step in building large language models (LLMs) that meet human needs.
Online Merging Optimizers for Boosting Rewards and Mitigating Tax in Alignment
Effectively aligning Large Language Models (LLMs) with human-centric values while preventing the degradation of abilities acquired through Pre-training and Supervised Fine-tuning (SFT) poses a central challenge in Reinforcement Learning from Human Feedback (RLHF).
Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignment
Nevertheless, we posit that LLMs inherently harbor role-play capabilities, owing to the extensive knowledge of characters and potential dialogues ingrained in their vast training corpora.
Routing to the Expert: Efficient Reward-guided Ensemble of Large Language Models
Zooter shows computation efficiency in inference as it introduces only a minor computation overhead of a routing function compared with reward model ranking methods.
Speculative Contrastive Decoding
Large language models~(LLMs) exhibit exceptional performance in language tasks, yet their auto-regressive inference is limited due to high computational requirements and is sub-optimal due to the exposure bias.
Self-Evolved Diverse Data Sampling for Efficient Instruction Tuning
The key to our data sampling technique lies in the enhancement of diversity in the chosen subsets, as the model selects new data points most distinct from any existing ones according to its current embedding space.
MuggleMath: Assessing the Impact of Query and Response Augmentation on Math Reasoning
In this paper, we conduct an investigation for such data augmentation in math reasoning and are intended to answer: (1) What strategies of data augmentation are more effective; (2) What is the scaling relationship between the amount of augmented data and model performance; and (3) Can data augmentation incentivize generalization to out-of-domain mathematical reasoning tasks?
Ranked #60 on
Arithmetic Reasoning
on GSM8K
(using extra training data)
How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition
We propose four intriguing research questions to explore the association between model performance and various factors including data amount, composition ratio, model size and SFT strategies.
Qwen Technical Report
Large language models (LLMs) have revolutionized the field of artificial intelligence, enabling natural language processing tasks that were previously thought to be exclusive to humans.
Ranked #3 on
Multi-Label Text Classification
on CC3M-TagMask
#InsTag: Instruction Tagging for Analyzing Supervised Fine-tuning of Large Language Models
Based on this observation, we propose a data selector based on InsTag to select 6K diverse and complex samples from open-source datasets and fine-tune models on InsTag-selected data.
Scaling Relationship on Learning Mathematical Reasoning with Large Language Models
We find with augmented samples containing more distinct reasoning paths, RFT improves mathematical reasoning performance more for LLMs.
Ranked #111 on
Arithmetic Reasoning
on GSM8K
(using extra training data)
PIVOINE: Instruction Tuning for Open-world Information Extraction
In particular, we construct INSTRUCTOPENWIKI, a substantial instruction tuning dataset for Open-world IE enriched with a comprehensive corpus, extensive annotations, and diverse instructions.
Exploring Partial Knowledge Base Inference in Biomedical Entity Linking
Biomedical entity linking (EL) consists of named entity recognition (NER) and named entity disambiguation (NED).
Multi-hop Evidence Retrieval for Cross-document Relation Extraction
Relation Extraction (RE) has been extended to cross-document scenarios because many relations are not simply described in a single document.
Knowledge-Enhanced Relation Extraction Dataset
Recently, knowledge-enhanced methods leveraging auxiliary knowledge graphs have emerged in relation extraction, surpassing traditional text-based approaches.
Summarization as Indirect Supervision for Relation Extraction
Considering that summarization tasks aim at acquiring concise expressions of synoptical information from the longer context, these tasks naturally align with the objective of RE, i. e., extracting a kind of synoptical information that describes the relation of entity mentions.
Ranked #7 on
Relation Extraction
on TACRED
BIOS: An Algorithmically Generated Biomedical Knowledge Graph
For decades, these knowledge graphs have been developed via expert curation; however, this method can no longer keep up with today's AI development, and a transition to algorithmically generated BioMedKGs is necessary.
Multimodal Learning on Graphs for Disease Relation Extraction
On a dataset annotated by human experts, REMAP improves text-based disease relation extraction by 10. 0% (accuracy) and 17. 2% (F1-score) by fusing disease knowledge graphs with text information.
High-throughput relation extraction algorithm development associating knowledge articles and electronic health records
In this paper, we present Hi-RES, a framework for high-throughput relation extraction algorithm development.
