Search Results for author:
Found 116 papers, 60 papers with code
Large Language Models Often Say One Thing and Do Another
As large language models (LLMs) increasingly become central to various applications and interact with diverse user populations, ensuring their reliable and consistent performance is becoming more important.
The Devil Is in the Details: Tackling Unimodal Spurious Correlations for Generalizable Multimodal Reward Models
Multimodal Reward Models (MM-RMs) are crucial for aligning Large Language Models (LLMs) with human preferences, particularly as LLMs increasingly interact with multimodal data.
DeepSolution: Boosting Complex Engineering Solution Design via Tree-based Exploration and Bi-point Thinking
Designing solutions for complex engineering challenges is crucial in human production activities.
Cheems: A Practical Guidance for Building and Evaluating Chinese Reward Models from Scratch
Reward models (RMs) are crucial for aligning large language models (LLMs) with human preferences.
SAISA: Towards Multimodal Large Language Models with Both Training and Inference Efficiency
To investigate whether attention among visual tokens is necessary, we propose a new self-attention mechanism, NAAViT (\textbf{N}o \textbf{A}ttention \textbf{A}mong \textbf{Vi}sual \textbf{T}okens), which eliminates this type of attention.
DeepRAG: Thinking to Retrieval Step by Step for Large Language Models
Large Language Models (LLMs) have shown remarkable potential in reasoning while they still suffer from severe factual hallucinations due to timeliness, accuracy, and coverage of parametric knowledge.
PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides
Automatically generating presentations from documents is a challenging task that requires balancing content quality, visual design, and structural coherence.
Auto-RT: Automatic Jailbreak Strategy Exploration for Red-Teaming Large Language Models
Automated red-teaming has become a crucial approach for uncovering vulnerabilities in large language models (LLMs).
The Rise and Down of Babel Tower: Investigating the Evolution Process of Multilingual Code Large Language Model
Based on our observations, we propose the Babel Tower Hypothesis, which describes the entire process of LLMs acquiring new language capabilities.
Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineering
The evolution of machine learning has increasingly prioritized the development of powerful models and more scalable supervision signals.
Transferable Post-training via Inverse Value Learning
After training this network on a small base model using demonstrations, this network can be seamlessly integrated with other pre-trained models during inference, enables them to achieve similar capability enhancements.
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).
StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization
Retrieval-augmented generation (RAG) is a key means to effectively enhance large language models (LLMs) in many knowledge-based tasks.
Multi-Facet Counterfactual Learning for Content Quality Evaluation
Evaluating the quality of documents is essential for filtering valuable content from the current massive amount of information.
Seg2Act: Global Context-aware Action Generation for Document Logical Structuring
Document logical structuring aims to extract the underlying hierarchical structure of documents, which is crucial for document intelligence.
Rethinking Reward Model Evaluation: Are We Barking up the Wrong Tree?
Reward Models (RMs) are crucial for aligning language models with human preferences.
READoc: A Unified Benchmark for Realistic Document Structured Extraction
Document Structured Extraction (DSE) aims to extract structured content from raw documents.
Critic-CoT: Boosting the reasoning abilities of large language model via Chain-of-thoughts Critic
Self-critic has become a crucial mechanism for enhancing the reasoning performance of LLMs.
CRUXEval-X: A Benchmark for Multilingual Code Reasoning, Understanding and Execution
However, there is an unignorable programming language bias in existing code benchmarks -- over 95% code generation benchmarks are dominated by Python, leaving the LLMs' capabilities in other programming languages such as Java and C/C++ unknown.
DOMAINEVAL: An Auto-Constructed Benchmark for Multi-Domain Code Generation
We notice that LLMs are generally good at computation tasks while falling short on cryptography and system coding tasks.
REInstruct: Building Instruction Data from Unlabeled Corpus
Manually annotating instruction data for large language models is difficult, costly, and hard to scale.
StructEval: Deepen and Broaden Large Language Model Assessment via Structured Evaluation
Evaluation is the baton for the development of large language models.
Beyond Correctness: Benchmarking Multi-dimensional Code Generation for Large Language Models
In recent years, researchers have proposed numerous benchmarks to evaluate the impressive coding capabilities of large language models (LLMs).
On-Policy Fine-grained Knowledge Feedback for Hallucination Mitigation
Previous learning-based methods focus on detecting knowledge boundaries and finetuning models with instance-level feedback, but they suffer from inaccurate signals due to off-policy data sampling and coarse-grained feedback.
Open Grounded Planning: Challenges and Benchmark Construction
In this paper, we propose a new planning task--open grounded planning.
Towards Scalable Automated Alignment of LLMs: A Survey
Alignment is the most critical step in building large language models (LLMs) that meet human needs.
Match, Compare, or Select? An Investigation of Large Language Models for Entity Matching
Based on our findings, we further design a compound entity matching framework (ComEM) that leverages the composition of multiple strategies and LLMs.
Base of RoPE Bounds Context Length
We revisit the role of RoPE in LLMs and propose a novel property of long-term decay, we derive that the \textit{base of RoPE bounds context length}: there is an absolute lower bound for the base value to obtain certain context length capability.
URL: Universal Referential Knowledge Linking via Task-instructed Representation Compression
Linking a claim to grounded references is a critical ability to fulfill human demands for authentic and reliable information.
Towards Universal Dense Blocking for Entity Resolution
Blocking is a critical step in entity resolution, and the emergence of neural network-based representation models has led to the development of dense blocking as a promising approach for exploring deep semantics in blocking.
Spiral of Silence: How is Large Language Model Killing Information Retrieval? -- A Case Study on Open Domain Question Answering
The practice of Retrieval-Augmented Generation (RAG), which integrates Large Language Models (LLMs) with retrieval systems, has become increasingly prevalent.
Few-shot Named Entity Recognition via Superposition Concept Discrimination
Then a superposition instance retriever is applied to retrieve corresponding instances of these superposition concepts from large-scale text corpus.
Meta-Cognitive Analysis: Evaluating Declarative and Procedural Knowledge in Datasets and Large Language Models
Declarative knowledge and procedural knowledge are two key parts in meta-cognitive theory, and these two hold significant importance in pre-training and inference of LLMs.
Academically intelligent LLMs are not necessarily socially intelligent
The academic intelligence of large language models (LLMs) has made remarkable progress in recent times, but their social intelligence performance remains unclear.
ShortGPT: Layers in Large Language Models are More Redundant Than You Expect
As Large Language Models (LLMs) continue to advance in performance, their size has escalated significantly, with current LLMs containing billions or even trillions of parameters.
Learning or Self-aligning? Rethinking Instruction Fine-tuning
Instruction Fine-tuning~(IFT) is a critical phase in building large language models~(LLMs).
SoFA: Shielded On-the-fly Alignment via Priority Rule Following
The alignment problem in Large Language Models (LLMs) involves adapting them to the broad spectrum of human values.
Self-Retrieval: End-to-End Information Retrieval with One Large Language Model
However, current interactions between IR systems and LLMs remain limited, with LLMs merely serving as part of components within IR systems, and IR systems being constructed independently of LLMs.
Executing Natural Language-Described Algorithms with Large Language Models: An Investigation
In this paper, we seek to examine the capacity of present-day LLMs to comprehend and execute algorithms outlined in natural language.
Rule or Story, Which is a Better Commonsense Expression for Talking with Large Language Models?
Building machines with commonsense has been a longstanding challenge in NLP due to the reporting bias of commonsense rules and the exposure bias of rule-based commonsense reasoning.
AI for social science and social science of AI: A Survey
Recent advancements in artificial intelligence, particularly with the emergence of large language models (LLMs), have sparked a rethinking of artificial general intelligence possibilities.
DBCopilot: Natural Language Querying over Massive Databases via Schema Routing
The development of Natural Language Interfaces to Databases (NLIDBs) has been greatly advanced by the advent of large language models (LLMs), which provide an intuitive way to translate natural language (NL) questions into Structured Query Language (SQL) queries.
Mitigating Large Language Model Hallucinations via Autonomous Knowledge Graph-based Retrofitting
Incorporating factual knowledge in knowledge graph is regarded as a promising approach for mitigating the hallucination of large language models (LLMs).
Toward Unified Controllable Text Generation via Regular Expression Instruction
Controllable text generation is a fundamental aspect of natural language generation, with numerous methods proposed for different constraint types.
Benchmarking Large Language Models in Retrieval-Augmented Generation
In this paper, we systematically investigate the impact of Retrieval-Augmented Generation on large language models.
ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases
Existing approaches to tool learning have either primarily relied on extremely large language models, such as GPT-4, to attain generalized tool-use abilities in a zero-shot manner, or utilized supervised learning to train limited scopes of tools on compact models.
Learning In-context Learning for Named Entity Recognition
M}$, and a new entity extractor can be implicitly constructed by applying new instruction and demonstrations to PLMs, i. e., $\mathcal{ (\lambda .
DLUE: Benchmarking Document Language Understanding
Understanding documents is central to many real-world tasks but remains a challenging topic.
Retentive or Forgetful? Diving into the Knowledge Memorizing Mechanism of Language Models
Memory is one of the most essential cognitive functions serving as a repository of world knowledge and episodes of activities.
Harvesting Event Schemas from Large Language Models
Event schema provides a conceptual, structural and formal language to represent events and model the world event knowledge.
Influence of External Information on Large Language Models Mirrors Social Cognitive Patterns
LLMs, as AI agents, can observe external information, which shapes their cognition and behaviors.
ChatGPT is a Knowledgeable but Inexperienced Solver: An Investigation of Commonsense Problem in Large Language Models
(4) Can ChatGPT effectively leverage commonsense for answering questions?
The Life Cycle of Knowledge in Big Language Models: A Survey
Knowledge plays a critical role in artificial intelligence.
Semantic-aware Contrastive Learning for More Accurate Semantic Parsing
Since the meaning representations are detailed and accurate annotations which express fine-grained sequence-level semtantics, it is usually hard to train discriminative semantic parsers via Maximum Likelihood Estimation (MLE) in an autoregressive fashion.
Universal Information Extraction as Unified Semantic Matching
Based on this paradigm, we propose to universally model various IE tasks with Unified Semantic Matching (USM) framework, which introduces three unified token linking operations to model the abilities of structuring and conceptualizing.
Bridging the Gap between Reality and Ideality of Entity Matching: A Revisiting and Benchmark Re-Construction
Experimental results demonstrate that the assumptions made in the previous benchmark construction process are not coincidental with the open environment, which conceal the main challenges of the task and therefore significantly overestimate the current progress of entity matching.
A Roadmap for Big Model
With the rapid development of deep learning, training Big Models (BMs) for multiple downstream tasks becomes a popular paradigm.
Few-shot Named Entity Recognition with Self-describing Networks
In this paper, we propose a self-describing mechanism for few-shot NER, which can effectively leverage illustrative instances and precisely transfer knowledge from external resources by describing both entity types and mentions using a universal concept set.
Can Prompt Probe Pretrained Language Models? Understanding the Invisible Risks from a Causal View
Prompt-based probing has been widely used in evaluating the abilities of pretrained language models (PLMs).
Unified Structure Generation for Universal Information Extraction
Information extraction suffers from its varying targets, heterogeneous structures, and demand-specific schemas.
Ranked #5 on
Aspect-Based Sentiment Analysis (ABSA)
on ASTE
(using extra training data)
ECO v1: Towards Event-Centric Opinion Mining
Events are considered as the fundamental building blocks of the world.
Pre-training to Match for Unified Low-shot Relation Extraction
Low-shot relation extraction~(RE) aims to recognize novel relations with very few or even no samples, which is critical in real scenario application.
Procedural Text Understanding via Scene-Wise Evolution
In this paper, we propose a new \textbf{scene-wise} paradigm for procedural text understanding, which jointly tracks states of all entities in a scene-by-scene manner.
CUGE: A Chinese Language Understanding and Generation Evaluation Benchmark
We argue that for general-purpose language intelligence evaluation, the benchmark itself needs to be comprehensive and systematic.
Progressive Adversarial Learning for Bootstrapping: A Case Study on Entity Set Expansion
Bootstrapping has become the mainstream method for entity set expansion.
Honey or Poison? Solving the Trigger Curse in Few-shot Event Detection via Causal Intervention
In this paper, we identify and solve the trigger curse problem in few-shot event detection (FSED) from a causal view.
Fine-grained Entity Typing via Label Reasoning
Conventional entity typing approaches are based on independent classification paradigms, which make them difficult to recognize inter-dependent, long-tailed and fine-grained entity types.
Ranked #8 on
Entity Typing
on Open Entity
Bridging the Gap between Language Model and Reading Comprehension: Unsupervised MRC via Self-Supervision
In this paper, we propose a new framework for unsupervised MRC.
Knowledgeable or Educated Guess? Revisiting Language Models as Knowledge Bases
Previous literatures show that pre-trained masked language models (MLMs) such as BERT can achieve competitive factual knowledge extraction performance on some datasets, indicating that MLMs can potentially be a reliable knowledge source.
Text2Event: Controllable Sequence-to-Structure Generation for End-to-end Event Extraction
Event extraction is challenging due to the complex structure of event records and the semantic gap between text and event.
Ranked #3 on
Event Extraction
on ACE2005
De-biasing Distantly Supervised Named Entity Recognition via Causal Intervention
Distant supervision tackles the data bottleneck in NER by automatically generating training instances via dictionary matching.
Denoising Distantly Supervised Named Entity Recognition via a Hypergeometric Probabilistic Model
Specifically, during neural network training, we naturally model the noise samples in each batch following a hypergeometric distribution parameterized by the noise-rate.
Element Intervention for Open Relation Extraction
Open relation extraction aims to cluster relation instances referring to the same underlying relation, which is a critical step for general relation extraction.
From Discourse to Narrative: Knowledge Projection for Event Relation Extraction
Current event-centric knowledge graphs highly rely on explicit connectives to mine relations between events.
From Paraphrasing to Semantic Parsing: Unsupervised Semantic Parsing via Synchronous Semantic Decoding
During synchronous decoding: the utterance paraphrasing is constrained by the structure of the logical form, therefore the canonical utterance can be paraphrased controlledly; the semantic decoding is guided by the semantics of the canonical utterance, therefore its logical form can be generated unsupervisedly.
Co-BERT: A Context-Aware BERT Retrieval Model Incorporating Local and Query-specific Context
BERT-based text ranking models have dramatically advanced the state-of-the-art in ad-hoc retrieval, wherein most models tend to consider individual query-document pairs independently.
Syntactic and Semantic-driven Learning for Open Information Extraction
One of the biggest bottlenecks in building accurate, high coverage neural open IE systems is the need for large labelled corpora.
Benchmarking Knowledge-Enhanced Commonsense Question Answering via Knowledge-to-Text Transformation
Experiments show that: (1) Our knowledge-to-text framework is effective and achieves state-of-the-art performance on CommonsenseQA dataset, providing a simple and strong knowledge-enhanced baseline for CQA; (2) The potential of knowledge is still far from being fully exploited in CQA -- there is a significant performance gap from current models to our models with golden knowledge; and (3) Context-sensitive knowledge selection, heterogeneous knowledge exploitation, and commonsense-rich language models are promising CQA directions.
From Bag of Sentences to Document: Distantly Supervised Relation Extraction via Machine Reading Comprehension
By re-organizing all sentences about an entity as a document and extracting relations via querying the document with relation-specific questions, the document-based DS paradigm can simultaneously encode and exploit all sentence-level, inter-sentence-level, and entity-level evidence.
Ranked #1 on
Relationship Extraction (Distant Supervised)
on NYT
Global Bootstrapping Neural Network for Entity Set Expansion
Bootstrapping for entity set expansion (ESE) has been studied for a long period, which expands new entities using only a few seed entities as supervision.
End-to-End Neural Event Coreference Resolution
Traditional event coreference systems usually rely on pipeline framework and hand-crafted features, which often face error propagation problem and have poor generalization ability.
ISCAS at SemEval-2020 Task 5: Pre-trained Transformers for Counterfactual Statement Modeling
ISCAS participated in two subtasks of SemEval 2020 Task 5: detecting counterfactual statements and detecting antecedent and consequence.
BERT-QE: Contextualized Query Expansion for Document Re-ranking
Query expansion aims to mitigate the mismatch between the language used in a query and in a document.
A Rigorous Study on Named Entity Recognition: Can Fine-tuning Pretrained Model Lead to the Promised Land?
Specifically, we erase name regularity, mention coverage and context diversity respectively from the benchmarks, in order to explore their impact on the generalization ability of models.
Overview of the CCKS 2019 Knowledge Graph Evaluation Track: Entity, Relation, Event and QA
Knowledge graph models world knowledge as concepts, entities, and the relationships between them, which has been widely used in many real-world tasks.
CAIL2019-SCM: A Dataset of Similar Case Matching in Legal Domain
In this paper, we introduce CAIL2019-SCM, Chinese AI and Law 2019 Similar Case Matching dataset.
EUSP: An Easy-to-Use Semantic Parsing PlatForm
Semantic parsing aims to map natural language utterances into structured meaning representations.
Learning to Bootstrap for Entity Set Expansion
Bootstrapping for Entity Set Expansion (ESE) aims at iteratively acquiring new instances of a specific target category.
Gazetteer-Enhanced Attentive Neural Networks for Named Entity Recognition
Current region-based NER models only rely on fully-annotated training data to learn effective region encoder, which often face the training data bottleneck.
Distilling Discrimination and Generalization Knowledge for Event Detection via Delta-Representation Learning
Event detection systems rely on discrimination knowledge to distinguish ambiguous trigger words and generalization knowledge to detect unseen/sparse trigger words.
Cost-sensitive Regularization for Label Confusion-aware Event Detection
In supervised event detection, most of the mislabeling occurs between a small number of confusing type pairs, including trigger-NIL pairs and sibling sub-types of the same coarse type.
Sequence-to-Nuggets: Nested Entity Mention Detection via Anchor-Region Networks
In this paper, we propose to resolve this problem by modeling and leveraging the head-driven phrase structures of entity mentions, i. e., although a mention can nest other mentions, they will not share the same head word.
Ranked #7 on
Nested Mention Recognition
on ACE 2005
Sentence Rewriting for Semantic Parsing
A major challenge of semantic parsing is the vocabulary mismatch problem between natural language and target ontology.
Overview of CAIL2018: Legal Judgment Prediction Competition
In this paper, we give an overview of the Legal Judgment Prediction (LJP) competition at Chinese AI and Law challenge (CAIL2018).
Sequence-to-Action: End-to-End Semantic Graph Generation for Semantic Parsing
This paper proposes a neural semantic parsing approach -- Sequence-to-Action, which models semantic parsing as an end-to-end semantic graph generation process.
Semi-Supervised Lexicon Learning for Wide-Coverage Semantic Parsing
Semantic parsers critically rely on accurate and high-coverage lexicons.
Model-Free Context-Aware Word Composition
Word composition is a promising technique for representation learning of large linguistic units (e. g., phrases, sentences and documents).
CAIL2018: A Large-Scale Legal Dataset for Judgment Prediction
In this paper, we introduce the \textbf{C}hinese \textbf{AI} and \textbf{L}aw challenge dataset (CAIL2018), the first large-scale Chinese legal dataset for judgment prediction.
Accurate Text-Enhanced Knowledge Graph Representation Learning
Previous representation learning techniques for knowledge graph representation usually represent the same entity or relation in different triples with the same representation, without considering the ambiguity of relations and entities.
Nugget Proposal Networks for Chinese Event Detection
Neural network based models commonly regard event detection as a word-wise classification task, which suffer from the mismatch problem between words and event triggers, especially in languages without natural word delimiters such as Chinese.
Adaptive Scaling for Sparse Detection in Information Extraction
This paper focuses on detection tasks in information extraction, where positive instances are sparsely distributed and models are usually evaluated using F-measure on positive classes.
Variational Recurrent Neural Machine Translation
Partially inspired by successful applications of variational recurrent neural networks, we propose a novel variational recurrent neural machine translation (VRNMT) model in this paper.
Reasoning with Heterogeneous Knowledge for Commonsense Machine Comprehension
Then we propose a multi-knowledge reasoning model, which selects inference rules for a specific reasoning context using attention mechanism, and reasons by summarizing all valid inference rules.
Context-Sensitive Inference Rule Discovery: A Graph-Based Method
Firstly, these methods are mostly context-insensitive, cannot accurately measure the similarity between two predicates in a specific context.
