← Search

Yaohui Jin

29 accepted papers

2026

The Overthinking Predicament: When Reasoning Hurts Ranking

ICLR 2026poster

Document reranking is a key component in information retrieval (IR), aimed at refining initial retrieval results to improve ranking quality for downstream tasks. Recent studies—motivated by large reasoning models (LRMs)—have begun incorporating explicit chain-of-thought (CoT) reasoning into LLM-base…

Cited by 0SourceScholar
2026

Tools are under-documented: Simple Document Expansion Boosts Tool Retrieval

ICLR 2026poster

Large Language Models (LLMs) have recently demonstrated strong capabilities in tool use, yet progress in tool retrieval remains hindered by incomplete and heterogeneous tool documentation. To address this challenge, we introduce Tool-DE, a new benchmark and framework that systematically enriches to…

Cited by 0SourcecodeScholar
2025

ChemActor: Enhancing Automated Extraction of Chemical Synthesis Actions with LLM-Generated Data

ACL 2025long

With the increasing interest in robotic synthesis in the context of organic chemistry, the automated extraction of chemical procedures from literature is critical. However, this task remains challenging due to the inherent ambiguity of chemical language and the high cost of human annotation required…

2025

Context Guided Transformer Entropy Modeling for Video Compression

ICCV 2025poster

Conditional entropy models effectively leverage spatio-temporal contexts to reduce video redundancy. However, incorporating temporal context often introduces additional model complexity and increases computational cost. In parallel, many existing spatial context models lack explicit modeling the ord…

2025

Faithful Self-Refinement in Mathematical Reasoning via Progressive Back-Translation

ICASSP 2025accepted

Large language models (LLMs) can achieve superior results through iterative refinement based on internal or external signals, compared to the unstable outputs from a single pass. However, the reliability of existing internal signals is questionable due to their susceptibility to intrinsic hallucinat…

Cited by 0SourceScholar
2025

Forest for the Trees: Overarching Prompting Evokes High-Level Reasoning in Large Language Models

NAACL 2025long

Chain-of-thought (CoT) and subsequent methods adopted a deductive paradigm that decomposes the reasoning process, demonstrating remarkable performances across NLP tasks. However, such a paradigm faces the challenge of getting bogged down in low-level semantic details, hindering large language models…

Cited by 0SourcePDFScholar
2025

KinFormer: Generalizable Dynamical Symbolic Regression for Catalytic Organic Reaction Kinetics

ICLR 2025poster

Modeling kinetic equations is essential for understanding the mechanisms of chemical reactions, yet a complex and time-consuming task. Kinetic equation prediction is formulated as a problem of dynamical symbolic regression (DSR) subject to physical chemistry constraints. Deep learning (DL) holds th…

Cited by 0SourcePDFScholar
2025

Look Before You Leap: Problem Elaboration Prompting Improves Mathematical Reasoning in Large Language Models

ICASSP 2025accepted

Large language models (LLMs) still grapple with complex tasks like mathematical reasoning. Despite significant efforts invested in improving prefix prompts or reasoning process, the crucial role of problem context might have been neglected. Accurate recognition of inputs is fundamental for solving m…

Cited by 0SourceScholar
2025

MultiConIR: Towards Multi-Condition Information Retrieval

EMNLP 2025

Multi-condition information retrieval (IR) presents a significant, yet underexplored challenge for existing systems. This paper introduces MultiConIR, the first benchmark specifically designed to evaluate retrieval and reranking models under nuanced multi-condition query scenarios across five divers

2025

PASG: A Closed-Loop Framework for Automated Geometric Primitive Extraction and Semantic Anchoring in Robotic Manipulation

ICCV 2025poster

The fragmentation between high-level task semantics and low-level geometric features remains a persistent challenge in robotic manipulation. While vision-language models (VLMs) have shown promise in generating affordance-aware visual representations, the lack of semantic grounding in canonical space…

Cited by 0SourcePDFScholar
2025

TopoRefine: Iterative Refinement with Reasoning Topology as High-Level Feedback

ICASSP 2025accepted

By leveraging effective signals to refine their outputs, large language models (LLMs) can achieve superior performance compared to single-pass outputs. However, internal signals often suffer from accumulated hallucinations and a lack of confidence, while external signals are typically difficult to o…

Cited by 0SourceScholar
2024

AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents

NeurIPS 2024oral

Evaluating large language models (LLMs) as general-purpose agents is essential for understanding their capabilities and facilitating their integration into practical applications. However, the evaluation process presents substantial challenges. A primary obstacle is the benchmarking of agent perform…

2024

Can Large Language Models Serve as Rational Players in Game Theory? A Systematic Analysis

AAAI 2024technical

Game theory, as an analytical tool, is frequently utilized to analyze human behavior in social science research. With the high alignment between the behavior of Large Language Models (LLMs) and humans, a promising research direction is to employ LLMs as substitutes for humans in game experiments, en…

Cited by 66SourcePDFScholar
2024

Comparable Demonstrations Are Important In In-Context Learning: A Novel Perspective On Demonstration Selection

ICASSP 2024accepted

In-Context Learning (ICL) is an important paradigm for adapting Large Language Models (LLMs) to downstream tasks through a few demonstrations. Despite the great success of ICL, the limitation of the demonstration number may lead to demonstration bias, i.e. the input-label mapping induced by LLMs mis…

Cited by 0SourceScholar
2023

Chain-of-Thought Tuning: Masked Language Models can also Think Step By Step in Natural Language Understanding

EMNLP 2023long main

Chain-of-Thought (CoT) is a technique that guides Large Language Models (LLMs) to decompose complex tasks into multi-step reasoning through intermediate steps in natural language form. Briefly, CoT enables LLMs to think step by step. However, although many Natural Language Understanding (NLU) tasks…

Cited by 0SourceScholar
2023

Improving the out-of-Distribution Generalization Capability of Language Models: Counterfactually-Augmented Data is not Enough

ICASSP 2023accepted

Counterfactually-Augmented Data (CAD) has the potential to improve language models’ Out-Of-Distribution (OOD) generalization capability, as CAD induces language models to exploit causal features and exclude spurious correlations. However, the empirical results of OOD generalization on CAD are not as…

Cited by 0SourceScholar
2023

Latent Constraints on Unsupervised Text-Graph Alignment with Information Asymmetry

AAAI 2023technical

Unsupervised text-graph alignment (UTGA) is a fundamental task that bidirectionally generates texts and graphs without parallel data. Most available models of UTGA suffer from information asymmetry, a common phenomenon that texts and graphs include additional information invisible to each other. On…

Cited by 0SourcePDFScholar
2023

MTR: A Dataset Fusing Inductive, Deductive, and Defeasible Reasoning

ACL 2023findings

A long-standing difficulty in AI is the introduction of human-like reasoning in machine reading comprehension. Since algorithmic models can already perform as well as humans on simple quality assurance tasks thanks to the development of deep learning techniques, more difficult reasoning datasets hav…

Cited by 1SourcePDFScholar
2023

Preference-Controlled Multi-Objective Reinforcement Learning for Conditional Text Generation

AAAI 2023technical

Conditional text generation is to generate text sequences conditioning on linguistic or non-linguistic data. The main line of existing work proposed deterministic models to improve the fidelity of the generated text but often ignored the diversity. Another line relied on conditional variational auto…

2023

Task-Level Thinking Steps Help Large Language Models for Challenging Classification Task

EMNLP 2023long main

Large language models (LLMs) have shown incredible performance on many tasks such as dialogue generation, commonsense reasoning and question answering. In-context learning (ICL) is an important paradigm for adapting LLMs to the downstream tasks by prompting few demonstrations. However, the distribut…

Cited by 0SourceScholar
2022

To What Extent Do Natural Language Understanding Datasets Correlate to Logical Reasoning? A Method for Diagnosing Logical Reasoning.

COLING 2022main

Reasoning and knowledge-related skills are considered as two fundamental skills for natural language understanding (NLU) tasks such as machine reading comprehension (MRC) and natural language inference (NLI). However, it is not clear to what extent an NLU task defined on a dataset correlates to a sp…

Cited by 5SourcePDFScholar
2022

Weakly Supervised Neural Symbolic Learning for Cognitive Tasks

AAAI 2022technical

Despite the recent success of end-to-end deep neural networks, there are growing concerns about their lack of logical reasoning abilities, especially on cognitive tasks with perception and reasoning processes. A solution is the neural symbolic learning (NeSyL) method that can effectively utilize pre…

Cited by 15SourcePDFScholar
2021

De-Confounded Variational Encoder-Decoder for Logical Table-to-Text Generation

ACL 2021long

Logical table-to-text generation aims to automatically generate fluent and logically faithful text from tables. The task remains challenging where deep learning models often generated linguistically fluent but logically inconsistent text. The underlying reason may be that deep learning models often…

2021

Dependent Multi-Task Learning with Causal Intervention for Image Captioning

IJCAI 2021poster

Recent work for image captioning mainly followed an extract-then-generate paradigm, pre-extracting a sequence of object-based features and then formulating image captioning as a single sequence-to-sequence task. Although promising, we observed two problems in generated captions: 1) content inconsist…

2021

Diagnosing the First-Order Logical Reasoning Ability Through LogicNLI

EMNLP 2021main

Recently, language models (LMs) have achieved significant performance on many NLU tasks, which has spurred widespread interest for their possible applications in the scientific and social area. However, LMs have faced much criticism of whether they are truly capable of reasoning in NLU. In this work…

Cited by 76SourcePDFScholar
2021

End-to-End Conversational Search for Online Shopping with Utterance Transfer

EMNLP 2021main

Successful conversational search systems can present natural, adaptive and interactive shopping experience for online shopping customers. However, building such systems from scratch faces real word challenges from both imperfect product schema/knowledge and lack of training dialog data. In this work…

2021

Synergetic Learning of Heterogeneous Temporal Sequences for Multi-Horizon Probabilistic Forecasting

AAAI 2021technical

Time-series is ubiquitous across applications, such as transportation, finance and healthcare. Time-series is often influenced by external factors, especially in the form of asynchronous events, making forecasting difficult. However, existing models are mainly designated for either synchronous time-…

Cited by 17SourcePDFScholar
2020

A Semantically Consistent and Syntactically Variational Encoder-Decoder Framework for Paraphrase Generation

COLING 2020main

Paraphrase generation aims to generate semantically consistent sentences with different syntactic realizations. Most of the recent studies rely on the typical encoder-decoder framework where the generation process is deterministic. However, in practice, the ability to generate multiple syntactically…