Papers by Ting Xiao

Event Representation Learning Enhanced with External Commonsense Knowledge (D19-1)

Challenge:	Existing methods fine-tune pre-trained models on cognitive data, ignoring the semantic gap between texts and cognitive signals.
Approach:	They propose a framework that can induce fine-grained cognitive features from cognitive data and incorporate them into pre-trained language models by adaptively adjusting the weight of cognitive features for different NLP tasks.
Outcome:	The proposed framework can induce fine-grained cognitive features from cognitive data and incorporate them into BERT by adaptively adjusting weight of cognitive features for different NLP tasks.

Copied to clipboard

Xiao Ding, Kuo Liao, Ting Liu, Zhongyang Li, Junwen Duan

Representation Learning

Challenge:	Existing methods to learn event representations from text lack commonsense knowledge about the intents and emotions of event participants.
Approach:	They propose to leverage external commonsense knowledge about the intent and sentiment of the event to learn distributed representations for structured events from text.
Outcome:	The proposed model improves on hard similarity tasks and yields more precise inferences on subsequent events under given contexts.

ReCo: Reliable Causal Chain Reasoning via Structural Causal Recurrent Neural Networks (2022.emnlp-main)

Copied to clipboard

Kai Xiong, Xiao Ding, Zhongyang Li, Li Du, Ting Liu, Bing Qin, Yi Zheng, Baoxing Huai

Stimulate the Critical Thinking of LLMs via Debiasing Discussion (2025.emnlp-main)

Challenge:	Causal chain reasoning models suffer from two main transitive problems: threshold effect and scene drift.
Approach:	They propose a framework that uses exogenous variables to represent causal pairs and estimates the threshold and scene contradictions using structural causal recurrent neural networks.
Outcome:	The proposed framework outperforms baselines on Chinese and English CCR datasets.

Copied to clipboard

Ruiyu Xiao, Lei Wu, Yuanxing Liu, Weinan Zhang, Ting Liu

Robustness in NLP

Challenge:	Existing studies show that large language models (LLMs) are often prone to stance homogeneity and human preference biases when faced with conflicting perspectives.
Approach:	They propose a novel two-stage training framework to address stance homogeneity bias and human preference bias by generating multi-model discussion datasets and optimizing reinforcement learning from human feedback to align with discussion correctness.
Outcome:	The proposed framework reduces stance homogeneity bias and human preference bias and improves generalization capabilities on non-discussion scenarios and out-of-domain datasets.

IFlyEA: A Chinese Essay Assessment System with Automated Rating, Review Generation, and Recommendation (2021.acl-demo)

Copied to clipboard

Jiefu Gong, Xiao Hu, Wei Song, Ruiji Fu, Zhichao Sheng, Bo Zhu, Shijin Wang, Ting Liu

Semantic Text Processing

Challenge:	Automated Essay Assessment (AEA) aims to judge students’ writing proficiency in an automatic way.
Approach:	They propose to use Chinese AEA system IFlyEssayAssess to evaluate essays written by native Chinese students from primary and junior schools.
Outcome:	The proposed system provides application services for essay scoring, review generation, recommendation, and explainable analytical visualization.

ExpeTrans: LLMs Are Experiential Transfer Learners (2025.acl-long)

Copied to clipboard

Jinglong Gao, Xiao Ding, Lingxiao Zou, Bibo Cai, Bing Qin, Ting Liu

Challenge:	Recent studies provide large language models with textual task-solving experiences via prompts to improve their performance.
Approach:	They propose to use prompts to provide LLMs with textual task-solving experiences during their inference stage.
Outcome:	The proposed framework improves the performance of large language models on 13 datasets.

Towards Generalizable and Faithful Logic Reasoning over Natural Language via Resolution Refutation (2024.lrec-main)

Copied to clipboard

Zhouhao Sun, Xiao Ding, Li Du, Bibo Cai, Jinglong Gao, Ting Liu, Bing Qin

Consolidation or Adaptation? PRISM: Disentangling SFT and RL Data via Gradient Concentration (2026.acl-long)

Challenge:	Large language models (LLMs) have achieved significant performance in various natural language reasoning tasks, but struggle with performing first-order logic reasoning over formal logical theories expressed in natural language.
Approach:	They propose a framework which introduces the paradigm of resolution refutation to solve first-order logic reasoning problems by extending reasoning rules and employing the principle of proof by contradiction.
Outcome:	The proposed framework outperforms existing models while maintaining performance in simple scenarios.

Copied to clipboard

Yang Zhao, Yangou Ouyang, Xiao Ding, Hepeng Wang, Bibo Cai, Kai Xiong, Jinglong Gao, Zhouhao Sun, Li Du, Bing Qin, Ting Liu

Yang Zhao, Li Du, Xiao Ding, Yangou Ouyang, Hepeng Wang, Kai Xiong, Jinglong Gao, Zhouhao Sun, Dongliang Xu, Qing Yang, Dongchen Li, Bing Qin, Ting Liu

Challenge:	Existing data arbitration strategies for large language model training rely on surface-level heuristics that fail to diagnose intrinsic learning needs.
Approach:	They propose a framework that arbitrates data based on its degree of cognitive conflict with the model's existing knowledge.
Outcome:	Extensive experiments on WebShop and ALFWorld show that PRISM outperforms state-of-the-art hybrid methods while reducing computational costs by up to 3.22 .

Copied to clipboard

Examining Inter-Consistency of Large Language Models Collaboration: An In-depth Analysis via Debate (2023.findings-emnlp)

Challenge:	Existing methods for selecting training data from general datasets fail to account for the joint distribution of instructions, resulting in inefficient learning and suboptimal knowledge transfer.
Approach:	They propose a method that constructs a mixed gradient-based instruction graph to capture the joint distribution and interdependencies among instructions.
Outcome:	The proposed method outperforms existing methods on domain adaptation tasks and in complex, data-scarce scenarios.

Copied to clipboard

Kai Xiong, Xiao Ding, Yixin Cao, Ting Liu, Bing Qin

Semantic Text Processing

Challenge:	Existing studies focus on inconsistency issues within a single LLM, while we explore the inter-consistencies among multiple LLMs for collaboration.
Approach:	They propose a formal debate framework to examine whether LLMs can collaborate effectively to achieve a consensus for a shared goal.
Outcome:	The proposed framework enables LLMs to achieve consensus in three real-world debate scenarios with real-time scenarios aligned to the LLM's goals.

Tool Zero: Training Tool-Augmented LLMs via Pure RL from Scratch (2025.findings-emnlp)

Copied to clipboard

Yirong Zeng, Xiao Ding, Yutai Hou, Yuxian Wang, Li Du, Juyi Dai, Qiuyang Ding, Duyu Tang, Dandan Tu, Weiwen Liu, Bing Qin, Ting Liu

Learning Sentence Representations over Tree Structures for Target-Dependent Classification (N18-1)

Challenge:	Experimental results demonstrate that our models achieve over 7% performance improvement compared to both SFT and RL-with-SFT models under the same experimental settings.
Approach:	They propose a dynamic generalization-guided reward design for rule-based RL that shifts rewards from exploratory to exploitative tool-use patterns.
Outcome:	The proposed model achieves over 7% performance improvement compared to SFT and RL-with-SFT models under the same experimental settings.

Copied to clipboard

Junwen Duan, Xiao Ding, Ting Liu

Information Extraction & Text Mining

Challenge:	Existing work on tree structures uses syntactic parsers or Treebank annotations to perform target-dependent classifications.
Approach:	They propose a reinforcement learning based approach which automatically induces target-specific sentence representations over tree structures.
Outcome:	The proposed model gives superior performance on two benchmark tasks compared to previous work on parsed trees .

Alleviating Hallucinations from Knowledge Misalignment in Large Language Models via Selective Abstention Learning (2025.acl-long)

Copied to clipboard

Lei Huang, Xiaocheng Feng, Weitao Ma, Yuchun Fan, Xiachong Feng, Yuxuan Gu, Yangfan Ye, Liang Zhao, Weihong Zhong, Baoxin Wang, Dayong Wu, Guoping Hu, Lingpeng Kong, Tong Xiao, Ting Liu, Bing Qin

MAESTRO: Meta-learning Adaptive Estimation of Scalarization Trade-offs for Reward Optimization (2026.acl-long)

Challenge:	Large language models (LLMs) suffer from severe hallucination issues due to the knowledge misalignment between the pre-training stage and the supervised fine-tuning stage.
Approach:	They propose a training objective with an abstention mechanism that selectively rejects tokens that misalign with the desired knowledge distribution via a special [REJ] token.
Outcome:	The proposed model selectively rejects tokens that misalign with the desired knowledge distribution via a special [REJ] token.

Copied to clipboard

Yang Zhao, Hepeng Wang, Xiao Ding, Yangou Ouyang, Bibo Cai, Kai Xiong, Jinglong Gao, Zhouhao Sun, Li Du, Bing Qin, Ting Liu

Green & Sustainable NLP

Challenge:	Group-Relative Policy Optimization (GRPO) has emerged as an efficient paradigm for aligning Large Language Models (LLMs), but its efficacy is confined to domains with verifiable ground truths.
Approach:	They propose a meta-cognitive orchestration layer that treats reward scalarization as a dynamic latent policy, leveraging the model’s terminal hidden states as 'a semantic bottleneck' . Across seven benchmarks, MAESTRO consistently outperforms single-reward and static multi-objective baselines while preserving the efficiency advantages of GRPO.
Outcome:	The proposed model outperforms single-reward and static multi-objective baselines while preserving efficiency advantages.

Adapting Where It Matters: Depth-Aware Adaptation for Efficient Multilingual Speech Recognition in Low-Resource Languages (2026.findings-acl)

Copied to clipboard

Yang Xiao, Eun-Jung Holden, Ting Dang

Neural Multitask Learning for Simile Recognition (D18-1)

Challenge:	Recent speech foundation models excel at multilingual automatic speech recognition (ASR) for high-resource languages, but their performance drops substantially on low-resourced languages due to the limited data availability.
Approach:	They propose a Depth-Aware Model Adaptation framework that allocates adaptation capacity according to each layer’s role.
Outcome:	The proposed framework matches or surpasses state-of-the-art accuracy with 80% fewer trainable parameters and achieves 29% error reduction under extreme data scarcity.

Copied to clipboard

Lizhen Liu, Xiao Hu, Wei Song, Ruiji Fu, Ting Liu, Guoping Hu

Information Extraction & Text Mining

Challenge:	Simile is a special type of metaphor, where comparators such as like and as are used to compare two objects.
Approach:	They propose a neural network framework for simile sentence classification, simile component extraction and language modeling.
Outcome:	The proposed framework outperforms rule-based and feature-based approaches in simile sentence classification and simile component extraction tasks.

e-CARE: a New Dataset for Exploring Explainable Causal Reasoning (2022.acl-long)

Copied to clipboard

Li Du, Xiao Ding, Kai Xiong, Ting Liu, Bing Qin

Dynamic Fusion Network for Multi-Domain End-to-end Task-Oriented Dialog (2020.acl-main)

Challenge:	Existing causal reasoning models only learn to induce empirical causal patterns that are predictive to the label, while human beings seek for deep and conceptual understanding of the causality to explain the observed causal facts.
Approach:	They present a human-annotated CAusal REasoning dataset with conceptual explanations of the causality.
Outcome:	The presented dataset shows that human-annotated explanations can be useful for promoting the accuracy and stability of causal reasoning models.

Copied to clipboard

Libo Qin, Xiao Xu, Wanxiang Che, Yue Zhang, Ting Liu

Dialogue Systems & Conversational Agents

Challenge:	Recent studies show remarkable success in end-to-end task-oriented dialog systems . however, most models rely on large training data, which is difficult to scalable for new domains with limited labeled data.
Approach:	They propose a shared-private network which exploits the relevance between the target domain and each domain.
Outcome:	The proposed model outperforms existing methods on multi-domain dialogue by 13.9% on average.

RU22Fact: Optimizing Evidence for Multilingual Explainable Fact-Checking on Russia-Ukraine Conflict (2024.lrec-main)

Copied to clipboard

Yirong Zeng, Xiao Ding, Yi Zhao, Xiangyu Li, Jie Zhang, Chao Yao, Ting Liu, Bing Qin

Prove Your Point!: Bringing Proof-Enhancement Principles to Argumentative Essay Generation (2024.emnlp-main)

Challenge:	Existing methods to verify factuality of claims do not provide sufficient evidence for explainable fact-checking systems.
Approach:	They propose a method to automatically retrieve and summarize evidence from the Web and a novel multilingual explainable fact-checking dataset on the Russia-Ukraine conflict in 2022.
Outcome:	The proposed method can retrieve and summarize evidence from the Web and generate explanations in 16 languages.

Copied to clipboard

Ruiyu Xiao, Lei Wu, Yuhang Gou, Weinan Zhang, Ting Liu

Challenge:	Existing arguments generation methods often overlook connections between opinions . Existing methods struggle with providing compelling proof .
Approach:	They propose a two-stage framework for argumentative essay generation with a focus on logical enhancement.
Outcome:	The proposed framework generates argumentative essays with better logical validity and persuasiveness than baseline models.

A Span-Extraction Dataset for Chinese Machine Reading Comprehension (D19-1)

Copied to clipboard

Yiming Cui, Ting Liu, Wanxiang Che, Li Xiao, Zhipeng Chen, Wentao Ma, Shijin Wang, Guoping Hu

Machine Reading Comprehension

Challenge:	Existing reading comprehension datasets are mostly in English . MRC is a new field of research that aims to comprehend the context of articles and answer the questions based on them.
Approach:	They propose a Span-Extraction dataset for Chinese machine reading comprehension to add language diversities to existing reading comprehension datasets.
Outcome:	The proposed dataset is composed of 20,000 real questions annotated on Wikipedia paragraphs by human experts.

Natural Logic at the Core: Dynamic Rewards for Entailment Tree Generation (2025.findings-acl)

Copied to clipboard

Jihao Shi, Xiao Ding, Kai Xiong, Hengwei Zhao, Bing Qin, Ting Liu

Bone Soups: A Seek-and-Soup Model Merging Approach for Controllable Multi-Objective Generation (2025.acl-long)

Challenge:	Existing approaches to generating entailment trees lack logical consistency . static reward structures or intricate dependencies within multi-step reasoning are often ignored .
Approach:	They propose a method that integrates natural logic principles into reinforcement learning to guide entailment tree generation.
Outcome:	Experiments on EntailmentBank show that the proposed method improves interpretability and generalization.

Copied to clipboard

Guofu Xie, Xiao Zhang, Ting Yao, Yunsheng Shi

Green & Sustainable NLP

Challenge:	Existing approaches focus on merging language models tuned on single objectives . existing approaches ignore the impacts of competing objectives on model tuning .
Approach:	They propose a model merging approach that seeks a series of backbone models and merges them according to user preferences.
Outcome:	The proposed approach exhibits strong controllability and Pareto optimality in controllable multi-objective generation.

MDC-Bench: A Multidisciplinary Causal Benchmark Based on Causal Structures for Evaluating Large Language Models (2026.findings-acl)

Copied to clipboard

Peng Wang, Yuxiong Yan, Xiao Ding, Kai Xiong, Bibo Cai, Chao Peng, Yutai Hou, Dandan Tu, Bing Qin, Ting Liu

Exploring Large Language Models for Effective Rumor Detection on Social Media (2025.naacl-long)

Challenge:	Existing causal datasets focus on the commonsense domain, but LLMs perform poorly when answering complex questions.
Approach:	They propose a multidisciplinary causal evaluation benchmark to assess LLMs' knowledge and skills.
Outcome:	The proposed model improves in domain specialization, structural diversity, and task complexity.

Copied to clipboard

Yirong Zeng, Xiao Ding, Bibo Cai, Ting Liu, Bing Qin

Self-Evolving GPT: A Lifelong Autonomous Experiential Learner (2024.acl-long)

Challenge:	Large-scale contexts hinder LLMs’ reasoning abilities while moderate contexts perform better for LLM.
Approach:	They propose a semantic-propagation collaboration-base framework that integrates small language models with LLMs for effective rumor detection.
Outcome:	The proposed framework bridges the gap between LLMs and LLM in facing long, structured data and offers a novel solution for rumor detection on social media.

Copied to clipboard

Jinglong Gao, Xiao Ding, Yiming Cui, Jianbai Zhao, Hepeng Wang, Ting Liu, Bing Qin

Neural Natural Logic Inference for Interpretable Question Answering (2021.emnlp-main)

Challenge:	Existing approaches to provide LLMs with textual task-solving experience rely on manual efforts to acquire and apply such experience for each task.
Approach:	They propose a lifelong autonomous experiential learning framework based on LLMs that learns and accumulates experience through experience transfer and induction.
Outcome:	The proposed framework performs reliably in each intermediate step and improves GPT-3.5 and GPT-4 on widely used NLP datasets.

Copied to clipboard

Jihao Shi, Xiao Ding, Li Du, Ting Liu, Bing Qin

GL-GIN: Fast and Accurate Non-Autoregressive Model for Joint Multiple Intent Detection and Slot Filling (2021.acl-long)

Challenge:	Existing question answering models are based on textual entailment tasks . prior work has focused on QA on premise-based questions .
Approach:	They propose a neural-symbolic QA approach that integrates natural logic reasoning within deep learning architectures towards developing effective question answering models.
Outcome:	The proposed model outperforms previous work on multiple-choice science questions . it integrates natural logic reasoning within deep learning architectures to build proof paths .

Copied to clipboard

Libo Qin, Fuxuan Wei, Tianbao Xie, Xiao Xu, Wanxiang Che, Ting Liu

Sentiment Analysis

Challenge:	Existing joint models for multi-intent SLU only consider intent detection while ignoring slot filling task.
Approach:	They propose a non-autoregressive model for joint multiple intent detection and slot filling . their framework is 11.5 times faster than existing joint models .
Outcome:	The proposed model is 11.5 times faster than existing models and is faster than current models.

Learning Target-Specific Representations of Financial News Documents For Cumulative Abnormal Return Prediction (C18-1)

Copied to clipboard

Junwen Duan, Yue Zhang, Xiao Ding, Ching-Yun Chang, Ting Liu

Representation Learning

Challenge:	Recent work considers learning dense representations for news titles and abstracts . text representations can address the sparsity of discrete indicators in statistical models .
Approach:	They propose to use news abstracts to combine the most informative sentences in news content to learn dense representations for text elements.
Outcome:	The proposed model can be used to estimate abnormal returns of companies when compared to titles and abstracts.

Deciphering the Impact of Pretraining Data on Large Language Models through Machine Unlearning (2024.findings-acl)

Copied to clipboard

Yang Zhao, Li Du, Xiao Ding, Kai Xiong, Zhouhao Sun, Shi Jun, Ting Liu, Bing Qin

Analyzing the Rapid Generalization of SFT via the Perspective of Attention Head Activation Patterns (2025.acl-long)

Challenge:	Existing studies have suggested that the composition of the pretraining corpus exerts a significant impact upon the performance of LLMs.
Approach:	They analyze the impact of 48 datasets from 5 major categories of pretraining data of Large Language Models and measure their impacts on LLMs using benchmarks about nine major categories.
Outcome:	The proposed analysis provides insights into the organization of data to support more efficient pretraining of Large Language Models.

Copied to clipboard

Yang Zhao, Li Du, Xiao Ding, Kai Xiong, Ting Liu, Bing Qin

Green & Sustainable NLP

Challenge:	Currently, LLMs learn in a data-driven schema while the instructions about complex tasks are both scarce and hard to collect or construct.
Approach:	They employ a gradient-based method to dissect the process that the Supervised Fine-tuning Process (SFT) adapts LLMs to downstream tasks via the perspective of attention patterns.
Outcome:	The proposed method dissects the process that the SFT process adapts LLMs to downstream tasks via the perspective of attention patterns.

Is ChatGPT a Good Causal Reasoner? A Comprehensive Evaluation (2023.findings-emnlp)

Copied to clipboard

Jinglong Gao, Xiao Ding, Bing Qin, Ting Liu

Towards Stable Natural Language Understanding via Information Entropy Guided Debiasing (2023.acl-long)

Challenge:	Existing methods to evaluate ChatGPT's causal reasoning abilities are based on pre-trained language models, but they rely on supervised training.
Approach:	They conduct the first comprehensive evaluation of ChatGPT’s causal reasoning capabilities using four state-of-the-art (STA) simulations.
Outcome:	The proposed model is not a good causal reasoner, but a great causal interpreter.

Copied to clipboard

Li Du, Xiao Ding, Zhouhao Sun, Ting Liu, Bing Qin, Jingshuo Liu

Robustness in NLP

Challenge:	Existing approaches to debiase Natural Language Understanding models use dataset biases instead of learning the intended task.
Approach:	They propose a debiasing framework that detects and purifies dataset biases using information entropy.
Outcome:	The proposed framework improves the stability of performance on out-of-distribution datasets for a set of widely adopted NLU models.

ExCAR: Event Graph Knowledge Enhanced Explainable Causal Reasoning (2021.acl-long)

Copied to clipboard

Li Du, Xiao Ding, Kai Xiong, Ting Liu, Bing Qin

Knowledge Representation

Challenge:	Existing work infers the causation between events based on knowledge from annotated causal event pairs, but additional evidence information is unexploited.
Approach:	They propose an Event graph knowledge enhanced explainable CAusal Reasoning framework that acquires additional evidence information from a large-scale causal event graph as logical rules for causal reasoning.
Outcome:	The proposed framework outperforms state-of-the-art methods in human evaluation and in animal models.

Com2 : A Causal-Guided Benchmark for Exploring Complex Commonsense Reasoning in Large Language Models (2025.acl-long)

Copied to clipboard

Kai Xiong, Xiao Ding, Yixin Cao, Yuxiong Yan, Li Du, Yufei Zhang, Jinglong Gao, Jiaqian Liu, Bing Qin, Ting Liu

STGN: an Implicit Regularization Method for Learning with Noisy Labels in Natural Language Processing (2022.emnlp-main)

Challenge:	Existing works focus on complex tasks like math and code, while complex commonsense reasoning remains underexplored due to its uncertainty and lack of structure.
Approach:	They propose to build a benchmark for large language models based on complex commonsense reasoning based upon causal event graphs and causal theory.
Outcome:	The proposed benchmark combines a complex commonsense reasoning benchmark with a detective story to achieve a more challenging subset.

Copied to clipboard

Tingting Wu, Xiao Ding, Minji Tang, Hao Zhang, Bing Qin, Ting Liu

Dynamic Low-rank Estimation for Transformer-based Language Models (2023.findings-emnlp)

Challenge:	Existing work to mitigate the effect of noisy labels is limited to specific tasks or training procedures, making it hard to be widely used.
Approach:	They propose a stochastic tailor-made gradient noise to mitigate the effect of noisy labels by introducing benign noise into stochistic gradient descent.
Outcome:	The proposed method can be used to discriminate correct samples from incorrect ones and boost existing training methods.

Copied to clipboard

Ting Hua, Xiao Li, Shangqian Gao, Yen-Chang Hsu, Yilin Shen, Hongxia Jin

NoisywikiHow: A Benchmark for Learning with Real-world Noisy Labels in Natural Language Processing (2023.findings-acl)

Challenge:	RankDyna is a matrix decomposition method that can be used to compress Transformer-based language models.
Approach:	They propose a matrix decomposition method that enables dynamic rank resource allocation . they say it can outperform current SOTA methods under various parameter budget levels .
Outcome:	The proposed method outperforms current SOTA methods under various budget levels . the proposed method is more efficient with higher compression rates .

Copied to clipboard

Tingting Wu, Xiao Ding, Minji Tang, Hao Zhang, Bing Qin, Ting Liu

Challenge:	Large-scale datasets in the real world often contain label noise, which can cause model overfitting and degrade generalization.
Approach:	They propose to use label noise to imitate human errors in annotations . they use a noisy label noise benchmark to evaluate their methods .
Outcome:	The proposed benchmarks are different from data with heterogeneous label noises in the real world.

Modeling Event Background for If-Then Commonsense Reasoning Using Context-aware Variational Autoencoder (D19-1)

Copied to clipboard

Li Du, Xiao Ding, Ting Liu, Zhongyang Li

Large Language Models Are Still Misled by Simple Bias Ensembles (2026.findings-acl)

Challenge:	Understanding event and event-centered commonsense reasoning is crucial for natural language processing (NLP).
Approach:	They propose a If-Then commonsense reasoning dataset Atomic and an RNN-based Seq2Seq model to facilitate this.
Outcome:	The proposed model improves the accuracy and diversity of inferences compared with baseline methods.

Copied to clipboard

Zhouhao Sun, Zhiyuan Kan, Xiao Ding, Li Du, Bibo Cai, Yang Zhao, Bing Qin, Ting Liu

iTool: Reinforced Fine-Tuning with Dynamic Deficiency Calibration for Advanced Tool Use (2025.emnlp-main)

Challenge:	Existing benchmarks for large language models are constrained to datasets where each sample is manually injected with only one type of bias.
Approach:	They propose a multi-bias benchmark where each sample contains multiple types of biases.
Outcome:	The proposed benchmark shows that existing LLMs and debiasing methods perform poorly on this benchmark, highlighting the challenge of eliminating compounded biases.

Copied to clipboard

Yirong Zeng, Xiao Ding, Yuxian Wang, Weiwen Liu, Yutai Hou, Wu Ning, Xu Huang, Duyu Tang, Dandan Tu, Bing Qin, Ting Liu