Jiangjie Chen

ThinkDial: An Open Recipe for Controlling Reasoning Effort in Large Language Models

Wed, 27 Aug 2025 00:00:00 +0000

MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent

Thu, 03 Jul 2025 00:00:00 +0000

ARIA: Training Language Agents with Intention-Driven Reward Aggregation

Sat, 31 May 2025 00:00:00 +0000

ORIGAMISPACE: Benchmarking Multimodal LLMs in Multi-Step Spatial Reasoning with Mathematical Constraints

Fri, 30 May 2025 00:00:00 +0000

Can LLMs Learn to Map the World from Local Descriptions?

Tue, 27 May 2025 00:00:00 +0000

Enigmata: Scaling Logical Reasoning in Large Language Models with Synthetic Verifiable Puzzles

Tue, 27 May 2025 00:00:00 +0000

KORGym: A Dynamic Game Platform for LLM Reasoning Evaluation

Tue, 20 May 2025 00:00:00 +0000

Seed-Thinking-v1.5: Advancing Superb Reasoning Models with Reinforcement Learning

Thu, 10 Apr 2025 00:00:00 +0000

DAPO: An Open-source LLM Reinforcement Learning System At Scale

Thu, 27 Mar 2025 00:00:00 +0000

PowerAttention: Exponentially Scaling of Receptive Fields for Effective Sparse Attention

Wed, 05 Mar 2025 00:00:00 +0000

DEEPER Insight into Your User: Directed Persona Refinement for Dynamic Persona Modeling

Sun, 16 Feb 2025 00:00:00 +0000

CoSER: Coordinating LLM-Based Persona Simulation of Established Roles

Thu, 13 Feb 2025 00:00:00 +0000

EASYTOOL: Enhancing LLM-based Agents with Concise Tool Instruction

Thu, 23 Jan 2025 00:00:00 +0000

EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms

Thu, 23 Jan 2025 00:00:00 +0000

Revealing the Barriers of Language Agents in Planning

Thu, 23 Jan 2025 00:00:00 +0000

SelfGoal: Your Language Agents Already Know How to Achieve High-level Goals

Thu, 23 Jan 2025 00:00:00 +0000

SEGMENT+: Long Text Processing with Short-Context Language Models

Tue, 08 Oct 2024 00:00:00 +0000

Past Meets Present: Creating Historical Analogy with Large Language Models

Tue, 24 Sep 2024 00:00:00 +0000

TravelAgent: An AI Assistant for Personalized Travel Planning

Thu, 12 Sep 2024 00:00:00 +0000

How Easily do Irrelevant Inputs Skew the Responses of Large Language Models?

Wed, 10 Jul 2024 00:00:00 +0000

DetectBench: Can Large Language Model Detect and Piece Together Implicit Evidence?

Sat, 15 Jun 2024 00:00:00 +0000

Evaluating Character Understanding of Large Language Models via Character Profiling from Fictional Works

Sun, 02 Jun 2024 00:00:00 +0000

From Persona to Personalization: A Survey on Role-Playing Language Agents

Tue, 30 Apr 2024 00:00:00 +0000

Character is Destiny: Can Large Language Models Simulate Persona-Driven Decisions in Role-Playing?

Sat, 20 Apr 2024 00:00:00 +0000

SurveyAgent: A Conversational System for Personalized and Efficient Research Survey

Wed, 10 Apr 2024 00:00:00 +0000

Agent Group Chat: An Interactive Group Chat Simulacra For Better Eliciting Collective Emergent Behavior

Wed, 20 Mar 2024 00:00:00 +0000

TimeArena: Shaping Efficient Multitasking Language Agents in a Time-Aware Simulation

Fri, 16 Feb 2024 00:00:00 +0000

InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews

Thu, 15 Feb 2024 00:00:00 +0000

GumbelSoft: Diversified Language Model Watermarking via the GumbelMax-trick

Wed, 14 Feb 2024 00:00:00 +0000

TravelPlanner: A Benchmark for Real-World Planning with Language Agents

Sun, 04 Feb 2024 00:00:00 +0000

Put Your Money Where Your Mouth Is: Evaluating Strategic Planning and Execution of LLM Agents in an Auction Arena

Tue, 10 Oct 2023 00:00:00 +0000

Translate Meanings, Not Just Words: IdiomKB's Role in Optimizing Idiomatic Translation with Language Models

Mon, 21 Aug 2023 00:00:00 +0000

Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts

Wed, 24 May 2023 00:00:00 +0000

Beneath Surface Similarity: Large Language Models Make Reasonable Scientific Analogies after Structure Abduction

Sun, 21 May 2023 00:00:00 +0000

AnalogyKB: Unlocking Analogical Reasoning of Language Models with A Million-scale Knowledge Base

Sun, 14 May 2023 00:00:00 +0000

Distilling Script Knowledge from Large Language Models for Constrained Language Planning

Tue, 02 May 2023 00:00:00 +0000

Say What You Mean! Large Language Models Speak Too Positively about Negative Commonsense Knowledge

Tue, 02 May 2023 00:00:00 +0000

Harnessing Knowledge and Reasoning for Human-Like Natural Language Generation: A Brief Review

Fri, 02 Dec 2022 00:00:00 +0000

Converge to the Truth: Factual Error Correction via Iterative Constrained Editing

Tue, 22 Nov 2022 00:00:00 +0000

Unsupervised Explanation Generation via Correct Instantiations

Tue, 22 Nov 2022 00:00:00 +0000

Neighbors Are Not Strangers: Improving Non-Autoregressive Translation under Low-Frequency Lexical Constraints

Fri, 08 Apr 2022 00:00:00 +0000

Theme I - Text Reasoning, Being Right for the Right Reasons 🤔

Sun, 27 Feb 2022 00:00:00 +0000

For humans, intuitive inferences are made every now and then. However, it would require reasons for humans to convince others and justify themselves of their inferences or decisions. How can machines better convince humans of their predictions? The key may lie in making the right and faithful reasons for self-justification.

What is human-like reasoning? What is the holy grail of machine cognition? It is easy to be right due to various spurious correlations, but it would require some actual reasoning skills to be right for the right and faithful reasons. More importantly, symbolic reasoning is too fragile to handle everyday reasoning. Can machine reasoning happen over natural language like humans do?

Exemplar papers in this theme include:

NEON (AAAI 2023): a two-phrase, unsupervised explanation generation framework for explaining why a statement is wrong;
E-KAR (Findings of ACL 2022): a benchmark for analogical reasoning with free-text rationales for both positive and negative candidate answers;
LOREN (AAAI 2022): generating faithful and accurate rationales without supervision;
EDUCAT (AAAI 2022): unsupervised counterfactual reasoning for imagining possible outcomes;
PRobr (Findings of ACL 2021): reasoning over natural language statements via an induced graphical model.

Theme II - Towards Factual, Controllable and Versatile Text Generation 🤖

Sun, 27 Feb 2022 00:00:00 +0000

The success of deep text generation is being held back by its non-factuality and difficulty to control. How to unleash the power of text generation models while restraining them from talking gibberish? In this research theme, we explore the potentials of text generation w.r.t. factuality and controllability.

To achieve these goals, one of the key perspectives is to incorporate various prior knowledge into neural models, including logical rules, templates, external knowledge bases, etc. Exemplar papers in this theme include:

VENCE (AAAI 2023): correcting factual errors in texts with the guidance of fact verification;
ACT (NAACL 2022): improving lexically constrained non-autoregressive machine translation, especially under low-frequency ones;
LOREN (AAAI 2022): interpretable fact verification against trustworthy knowledge bases;
FalCon (DASFAA 2022): faithful response generation with contrastive learning;
KeDy (WSDM 2022) and Keep (NLPCC 2021): diversified generation guided by knowledge graphs;
HedModTmpl (ACL 2019): generating faithful entity type descriptions constrained by head-modifier templates.

E-KAR: A Benchmark for Rationalizing Natural Language Analogical Reasoning

Thu, 24 Feb 2022 00:00:00 +0000

FalCon: A Faithful Contrastive Framework for Response Generation in TableQA Systems

Wed, 23 Feb 2022 00:00:00 +0000

LOREN: Logic-Regularized Reasoning for Interpretable Fact Verification

Tue, 22 Feb 2022 00:00:00 +0000

Unsupervised Editing for Counterfactual Stories

Tue, 22 Feb 2022 00:00:00 +0000

Diversified Query Generation Guided with Knowledge Graph

Mon, 21 Feb 2022 00:00:00 +0000

Harvesting More Answer Spans from Paragraphs beyond Annotation

Mon, 21 Feb 2022 00:00:00 +0000

Diversified Paraphrase Generation with Commonsense Knowledge Graph

Fri, 15 Oct 2021 00:00:00 +0000

Probabilistic Graph Reasoning for Natural Proof Generation

Fri, 30 Jul 2021 00:00:00 +0000

Ensuring Readability and Data-fidelity using Head-modifier Templates in Deep Type Description Generation

Tue, 30 Jul 2019 00:00:00 +0000

CN-Probase: A Data-driven Approach for Large-scale Chinese Taxonomy Construction

Mon, 08 Apr 2019 00:00:00 +0000