United States

With Large Language Model (LLM) agents taking on more evaluation responsibilities in decision-making, it is essential to recognize their possible biases to guarantee fair and trust- worthy AI-supported decisions. This study is the first to thoroughly examine the choice-supportive bias in LLM agents, a cognitive bias that is known to impact human decisionmaking and evaluation. We conduct experiments across 19 open/unopen-source LLM models in five scenarios at maximum, employing both memory-based and evaluation-based tasks adapted and redesigned from human cognitive studies. Our findings show that LLM agents may exhibit biased attribution or evaluation that supports their initial choices, and such bias may persist even if contextual hallucination is not observable. Key findings show that bias manifestation can differ greatly depending on prompt construction and context preservation, and the bias may be mitigated in larger models. Significantly, we observe that the bias increases when the agents perceive they are in control. Our extensive study involving 301 well-educated humans shows that, despite bias, certain LLM agents can still perform better than humans in similar evaluation tasks. This research contributes to the growing area of AI psychology, and the findings underscore the importance of addressing cognitive biases in LLM Agent systems, with wide-ranging implications spanning from improving AI-assisted decision-making to advancing AI safety and ethics.

AAAI 2025

LLM Agents Can Be Choice-Supportive Biased Evaluators: An Empirical Study

other foundations of humans ai

## Welcome to EMNLP 2024! 
We are excited to welcome you to one of the most prominent conferences in the field of Natural Language Processing. This year, EMNLP 2024 is being held in a hybrid format,
offering both virtual and in-person participation in beautiful Miami. Due to a record-breaking number of submissions, we've expanded the total number of accepted papers to accommodate more cutting-edge research from around the globe.
### [Conference Handbook](https://drive.google.com/file/d/1WPROgxjLAC96AJL7Ugy0tEnYm7dkrbHt/view?usp=sharing)

You are required to register for this event. **Please register [here](https://2024.emnlp.org/registration/).** The EMNLP 2024 event page on Underline will be open to public one week prior to the event.

Please register!

EMNLP 2024

EMNLP 2024 will take place in Miami, Florida from Nov 12th to Nov 16th, 2024, at the Hyatt Regency Miami Hote and on Underline for remote participants.

technical paper

We are pleased to announce the Thirty-Ninth AAAI Conference on Artificial Intelligence (AAAI-25), which will be held in Philadelphia, Pennsylvania at the Pennsylvania Convention Center from February 25 to March 4, 2025.

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-25 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.

### [Invited Speakers](https://aaai.org/conference/aaai/aaai-25/aaai-25-invited-speakers/)

Register [here](https://aaai.org/conference/aaai/aaai-25/registration/)

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-25 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.



Cryo-electron microscopy (cryo-EM) has revolutionized the field of structural biology, determining structures of large protein machines and sharpening the understanding of fundamental biological processes. Despite cryo-EM’s unique capacity to discover novel proteins from unpurified samples and reveal the intricate structures of protein complexes within native cellular environments, the advancement of protein identification methods for cryo-EM lags behind. Without prior knowledge, such as sequence, protein identification from low-resolution density maps remains challenging. Here we introduce CryoDomain, an innovative method for identifying protein domains — conserved constituent units of proteins — from low-resolution cryo-EM density maps without requiring prior knowledge of protein sequences. CryoDomain leverages cross-modal alignment to correlate cryo-EM density maps with atomic structures, transferring the knowledge learned on a large atomic structure dataset to a sparse density map dataset. On two protein domain benchmarks constructed from CATH and SCOPe, CryoDomain significantly outperforms the state-of-the-art methods for domain identification from low-resolution density maps. CryoDomain liberates structural biologists from the tedious tasks of density inspection and database searching during protein identification. It has the potential to extend the border of unbiased structure discovery and cellular landscape investigation using cryo-EM.

CryoDomain: Sequence-free Protein Domain Identification from Low-resolution Cryo-EM Density Maps

The clique partitioning problem (CPP) aims to find a partition of vertices of a complete graph in order to maximize the sum of edge weights within each partition (clique), which has been proven to be NP-hard and has wide real-world applications. In this paper, we propose an elite-guided weighted simulated annealing algorithm called EWSA to solve the CPP. First, EWSA employs two specific configurations and alternates between them via an oscillation strategy, which balances the exploitation and exploration of the search. Second, a weighting strategy is introduced to improve the scoring function in traditional simulated annealing, which is able to guide the search to explore diverse solutions. Finally, a partition restriction strategy is adopted to reduce search space and increase the search efficiency. Experiments on 255 instances demonstrate the competitiveness of EWSA. For 130 open instances, EWSA discovers new upper bounds in 32 cases and matches the best known results for the others. For the remaining 125 closed instances, EWSA achieves the best known objective values within a short computational time.

An Elite-guided Weighted Simulated Annealing Algorithm for the Clique Partitioning Problem

Explainable AI increasingly relies on argumentation methods to facilitate interactive explanations between AI agents and human users. While most works assume a known human user model as a prior, there is a critical gap in effectively learning and updating these models dynamically. In this paper, we address this gap with a framework that enables AI agents to learn and update probabilistic human models through argumentation-based dialogues. Specifically, our approach, called Persona, is inspired by prospect theory and integrates a probability weighting function with a Bayesian belief update mechanism that refines a probability distribution over possible human models based on exchanged arguments. Through empirical evaluations with human users in an applied argumentation setting, we demonstrate the effectiveness of Persona in capturing evolving human beliefs and facilitating personalized interactions, while also outperforming state-of-the-art methods.

Does Your AI Agent Get You? A Personalizable Framework for Approximating Human Models from Argumentation-based Dialogue Traces

Sequential Recommender Systems (SRS), which model a user's interaction history to predict the next item of interest, are widely used in various applications. However, existing SRS often struggle with low-popularity items, a challenge known as the long-tail problem. This issue leads to reduced serendipity for users and diminished profits for sellers, ultimately harming the overall system. Large Language Model (LLM) has the ability to capture semantic relationships between items, independent of their popularity, making them a promising solution to this problem. In this paper, we introduce __LLMEmb__, a novel method leveraging LLM to generate item embeddings that enhance SRS performance. To bridge the gap between general-purpose LLM and the recommendation domain, we propose a Supervised Contrastive Fine-Tuning (SCFT) approach. This approach includes attribute-level data augmentation and a tailored contrastive loss to make LLM more recommendation-friendly. Additionally, we emphasize the importance of integrating collaborative signals into LLM-generated embeddings, for which we propose Recommendation Adaptation Training (RAT). This further refines the embeddings for optimal use in SRS. The LLMEmb-derived embeddings can be seamlessly integrated with any SRS model, underscoring the practical value. Comprehensive experiments conducted on three real-world datasets demonstrate that LLMEmb significantly outperforms existing methods across multiple SRS models. The code for our method is provided in the __Supplementary Materials__.

LLMEmb: Large Language Model Can Be a Good Embedding Generator for Sequential Recommendation

Text-to-SQL enables users to interact with databases through natural language, simplifying the retrieval and synthesis of information. Despite the success of large language models (LLMs) in converting natural language questions into SQL queries, their broader adoption is limited by two main challenges: achieving robust generalization across diverse queries and ensuring interpretative confidence in their predictions. To tackle these issues, our research investigates the integration of selective classifiers into text-to-SQL systems. 
We analyse the trade-off between coverage and risk using entropy based confidence estimation with selective classifiers and assess its impact on the overall performance of text-to-SQL models.  Additionally, we explore the models' initial calibration and improve it with calibration techniques for better model alignment between confidence and accuracy.  Our experimental results show that encoder-decoder T5 is better calibrated than in-context-learning GPT 4 and decoder-only Llama 3, thus the designated external entropy-based selective classifier has better performance.  The study also reveal that, in terms of error detection, selective classifier with a higher probability detects errors associated with irrelevant questions rather than incorrect query generations.

Confidence Estimation for Error Detection in Text-to-SQL Systems

Opponent Modeling (OM) aims to enhance decision-making by modeling other agents in multi-agent environments. Existing works typically learn opponent models against a pre-designated fixed set of opponents during training. However, this will cause poor generalization when facing unknown opponents during testing, as previously unseen opponents can exhibit out-of-distribution (OOD) behaviors that the learned opponent models cannot handle. To tackle this problem, we introduce a novel Open-Ended Opponent Modeling (OEOM) framework, which continuously generates opponents with diverse strengths and styles to reduce the possibility of OOD situations occurring during testing. Founded on population-based training and information-theoretic trajectory space diversity regularization, OEOM generates a dynamic set of opponents. This set is then fed to any OM approaches to train a potentially generalizable opponent model. Upon this, we further propose a simple yet effective OM approach that naturally fits within the OEOM framework. This approach is based on in-context reinforcement learning and learns a Transformer that dynamically recognizes and responds to opponents based on their trajectories. Extensive experiments in cooperative, competitive, and mixed environments demonstrate that OEOM is an approach-agnostic framework that improves generalizability compared to training against a fixed set of opponents, regardless of OM approaches or testing opponent settings. The results also indicate that our proposed approach generally outperforms existing OM baselines.

An Open-Ended Learning Framework for Opponent Modeling

Model editing aims to correct outdated or erroneous knowledge in large models without costly retraining. Recent research discovered that the mid-layer representation of the subject's final token in a prompt has a strong influence on factual predictions, and developed Large Language Model (LLM) editing techniques based on this observation. However, for Vision-LLMs (VLLMs), how visual representations impact the predictions from a decoder-only language model remains largely unexplored. To the best of our knowledge, model editing for VLLMs has not been extensively studied in the literature. In this work, we employ the contribution allocation and noise perturbation methods to measure the contributions of visual representations for token predictions. Our attribution analysis shows that visual representations in mid-to-later layers that are highly relevant to the prompt contribute significantly to predictions. Based on these insights, we propose *VisEdit*, a novel model editor for VLLMs that effectively corrects knowledge by editing intermediate visual representations in regions important to the edit prompt. We evaluated *VisEdit* using multiple VLLM backbones and public VLLM editing benchmark datasets. The results show the superiority of *VisEdit* over the strong baselines adapted from existing state-of-the-art editors for LLMs.

Attribution Analysis Meets Model Editing: Advancing Knowledge Correction in Vision Language Models with VisEdit

Spatially Resolved Transcriptomics (SRT) has become an indispensable tool in various fields, including tumor micro-environment identification, neurobiology, and the study of complex tissue architecture.  However, the accuracy of these insights is often compromised by noise in spatial transcriptomics data due to technical limitations. While recent advancements in denoising methods have shown some promise, they frequently fall short by neglecting spatial features, overlooking the variability in noise levels among genes, and relying heavily on external histological images for supplementary information. In our study, we propose DUSTED, a Dual-Attention Enhanced Spatial Transcriptomics Denoiser, designed to address these challenges. Built on a graph autoencoder framework, DUSTED utilizes gene channel attention and graph attention mechanisms to simultaneously consider spatial features and noise variability in gene expression data. Additionally, it integrates prior biological knowledge, ensuring a more accurate fit for gene expression distributions. Benchmark tests using simulated datasets demonstrate that DUSTED outperforms existing methods. Furthermore, in real-world applications with the HOCWTA and DLPFC datasets, DUSTED excels in enhancing the correlation between gene and protein expression, recovering spatial gene expression patterns, and improving clustering results. These improvements underscore its potential impact on advancing our understanding of tumor micro-environments, neural tissue organization, and other biologically significant areas.

DUSTED: Dual-Attention Enhanced Spatial Transcriptomics Denoiser

Traditional recurrent neural network architectures, such as long short-term memory neural networks (LSTM), have historically held a prominent role in time series forecasting (TSF) tasks. While the recently introduced sLSTM for Natural Language Processing (NLP) introduces exponential gating and memory mixing that are beneficial for long term sequential learning, its potential short memory issue is a barrier to applying sLSTM directly in TSF. To address this, we propose a simple yet efficient algorithm named P-sLSTM, which is built upon sLSTM by incorporating patching and channel independence. These modifications substantially enhance sLSTM's performance in TSF, achieving state-of-the-art results. Furthermore, we provide theoretical justifications for our design, and conduct extensive comparative and analytical experiments to fully validate the efficiency and superior performance of our model.

Unlocking the Power of LSTM for Long Term Time Series Forecasting

Multifaceted user modeling aims to uncover fine-grained patterns and learn representations from user data, revealing their multifaceted interests and characteristics, such as profile, preference, and personality. Recent works on foundation model-based recommendation have highlighted the Transformer architecture's exceptional ability to capture non-linear user-item interaction relationships. This paper aims to improve the foundation models-based recommendation system by enhancing multi-faceted user modeling capabilities. We propose a novel Transform layer specifically designed for recommendation that uses the self-attention mechanism to capture sequential user-item interaction patterns. Additionally, we incorporate a group gating network to effectively identify user groups. Thus, we will hierarchically discover user groups in different layers that approximately capture the multi-faceted user interests within multiple Transformer layers. Moreover, to leverage a wider range of data and enhance multifaceted user modeling, we extend the application scenario to be compatible with a federated setting for leveraging private datasets with privacy preservation. Experimental validations on benchmark datasets demonstrate the superior performance of our proposed method.

Downloads

Next from AAAI 2025

CryoDomain: Sequence-free Protein Domain Identification from Low-resolution Cryo-EM Density Maps

Similar lecture

Cognitive Bias in Decision-Making with LLMs

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AAAI 2025

CryoDomain: Sequence-free Protein Domain Identification from Low-resolution Cryo-EM Density Maps

Similar lecture

Cognitive Bias in Decision-Making with LLMs

Downloads