United States

By integrating external knowledge, Retrieval-Augmented Generation (RAG) has become an effective strategy for mitigating the hallucination problems that large language models (LLMs) encounter when dealing with knowledge-intensive tasks. However, in the process of integrating external non-parametric supporting evidence with internal parametric knowledge, inevitable knowledge conflicts may arise, leading to confusion in the model&#39;s responses. To enhance the knowledge selection of LLMs in various contexts, some research has focused on refining their behavior patterns through instruction-tuning. Nonetheless, due to the absence of explicit negative signals and comparative objectives, models fine-tuned in this manner may still exhibit undesirable behaviors such as contextual ignorance and contextual overinclusion. To this end, we propose a Knowledge-aware Preference Optimization strategy, dubbed KnowPO, aimed at achieving adaptive knowledge selection based on contextual relevance in real retrieval scenarios. Concretely, we proposed a general paradigm for constructing knowledge conflict datasets, which comprehensively cover various error types and learn how to avoid these negative signals through preference optimization methods. Simultaneously, we proposed a rewriting strategy and data ratio optimization strategy to address preference imbalances. Experimental results show that KnowPO outperforms previous methods for handling knowledge conflicts by over 37%, while also exhibiting robust generalization across various out-of-distribution datasets.

AAAI 2025

KnowPO: Knowledge-Aware Preference Optimization for Controllable Knowledge Selection in Retrieval-Augmented Language Models

snlp

language models

## Welcome!
"I am excited to welcome you to this year’s edition of the Conference on Empirical Methods in Natural Language Processing! Importantly, it marks the 30th edition of EMNLP. With over 8,000 submissions, more than 3,000 accepted papers, and thousands of attendees, we have come a long way from that first
workshop, which had 14 accepted papers. As the field looks ahead, Suzhou is the fitting location for celebrating this milestone: rooted in a long literary tradition, yet modern and forward-looking, and home to a large share of the NLP community." 

*Message from the General Chair, Dirk Hovy*

EMNLP 2025

Celebrate 30 Years of EMNLP! 
EMNLP 2025 will be held in Suzhou, China from November 5th to November 9th, 2025.

By integrating external knowledge, Retrieval-Augmented Generation (RAG) has become an effective strategy for mitigating the hallucination problems that large language models (LLMs) encounter when dealing with knowledge-intensive tasks. However, in the process of integrating external non-parametric supporting evidence with internal parametric knowledge, inevitable knowledge conflicts may arise, leading to confusion in the model's responses. To enhance the knowledge selection of LLMs in various contexts, some research has focused on refining their behavior patterns through instruction-tuning. Nonetheless, due to the absence of explicit negative signals and comparative objectives, models fine-tuned in this manner may still exhibit undesirable behaviors such as contextual ignorance and contextual overinclusion. To this end, we propose a Knowledge-aware Preference Optimization strategy, dubbed KnowPO, aimed at achieving adaptive knowledge selection based on contextual relevance in real retrieval scenarios. Concretely, we proposed a general paradigm for constructing knowledge conflict datasets, which comprehensively cover various error types and learn how to avoid these negative signals through preference optimization methods. Simultaneously, we proposed a rewriting strategy and data ratio optimization strategy to address preference imbalances. Experimental results show that KnowPO outperforms previous methods for handling knowledge conflicts by over 37%, while also exhibiting robust generalization across various out-of-distribution datasets.

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.



We introduce Limited Rollout Beam Search (LRBS), a beam search strategy for deep reinforcement learning (DRL) based combinatorial optimization improvement heuristics. 
Utilizing pre-trained models on the Euclidean Traveling Salesperson Problem, LRBS significantly enhances both in-distribution performance and generalization to larger problem instances, achieving optimality gaps that outperform existing improvement heuristics and narrowing the gap with state-of-the-art constructive methods.
We also extend our analysis to two pickup and delivery TSP variants to validate our results.
Finally, we employ our search strategy for offline and online adaptation of the pre-trained improvement policy, leading to improved search performance and surpassing recent adaptive methods for constructive heuristics. Our source code is available at anonymous-url.

Scaling Combinatorial Optimization Neural Improvement Heuristics with Online Search and Adaptation

There has been tremendous progress in the past decade in the
field of quantified Boolean formulas (QBF), both in practical
solving as well as in creating a theory of corresponding proof
systems and their proof complexity analysis. Both for solving
and for proof complexity, it is important to have interesting
formula families on which we can test solvers and gauge the
strength of the proof systems. There are currently few such
formula families in the literature.
We initiate a general programme how to transform computationally
hard problems (located in the polynomial hierarchy)
into QBFs hard for the main QBF resolution systems Q-Res
and QU-Res that relate to core QBF solvers. We illustrate
this general approach on three problems from graph theory
and logic. This yields QBF families that are provably hard for
Q-Res and QU-Res (without any complexity assumptions).

Computationally Hard Problems Are Hard for QBF Proof Systems Too

We introduce Neural Conjugate Flows (NCF), a class of neural-network architectures equipped with exact flow structure. By leveraging topological conjugation, we prove that these networks are not only naturally isomorphic to a continuous group, but are also universal approximators for flows of ordinary differential equation (ODEs). Furthermore, topological properties of these flows can be enforced by the architecture in an interpretable manner. We demonstrate in numerical experiments how this topological group structure leads to concrete computational gains over other physics informed neural networks in estimating and extrapolating latent dynamics of ODEs, while training up to five times faster than other flow-based architectures.

Neural Conjugate Flows: A Physics-Informed Architecture with Flow Structure

Gaussian Splatting (GS) has emerged as a crucial technique for representing discrete volumetric radiance fields. It leverages unique parametrization to mitigate computational demands in scene optimization. This work introduces Topology-Aware 3D Gaussian Splatting (Topology-GS), which addresses two key limitations in current approaches: compromised pixel-level structural integrity due to incomplete initial geometric coverage, and inadequate feature-level integrity from insufficient topological constraints during optimization. To overcome these limitations, Topology-GS incorporates a novel interpolation strategy, Local Persistent Voronoi Interpolation (LPVI), and a topology-focused regularization term based on persistent barcodes, named PersLoss. LPVI utilizes persistent homology to guide adaptive interpolation, enhancing point coverage in low-curvature areas while preserving topological structure. PersLoss aligns the visual perceptual similarity of rendered images with ground truth by constraining distances between their topological features. Comprehensive experiments on three novel-view synthesis benchmarks demonstrate that Topology-GS outperforms existing methods in terms of PSNR, SSIM, and LPIPS metrics, while maintaining efficient memory usage. This study pioneers the integration of topology with 3D-GS, laying the groundwork for future research in this area.

Topology-Aware 3D Gaussian Splatting: Leveraging Persistent Homology for Optimized Structural Integrity

Multimodal Sentiment Analysis (MSA) stands as a critical research frontier, seeking to comprehensively unravel human emotions by amalgamating text, audio, and visual data. Yet, discerning subtle emotional nuances within audio and video expressions poses a formidable challenge, particularly when emotional polarities across various segments appear similar. In this paper, our objective is to spotlight emotion-relevant attributes of audio and visual modalities to facilitate multimodal fusion in the context of nuanced emotional shifts in visual-audio scenarios. To this end, we introduce DEVA, a progressive fusion framework founded on textual sentiment descriptions aimed at accentuating emotional features of visual-audio content. DEVA employs an Emotional Description Generator (EDG) to transmute raw audio and visual data into textualized sentiment descriptions, thereby amplifying their emotional characteristics. These descriptions are then integrated with the source data to yield richer, enhanced features. Furthermore, DEVA incorporates the Text-guided Progressive Fusion Module (TPF), leveraging varying levels of text as a core modality guide. This module progressively fuses visual-audio minor modalities to alleviate disparities between text and visual-audio modalities. Experimental results on widely-used sentiment analysis benchmark datasets, including MOSI, MOSEI, and CH-SIMS, underscore significant enhancements compared to state-of-the-art models. Moreover, fine-grained emotion experiments corroborate the robust sensitivity of DEVA to subtle emotional variations.

Enriching Multimodal Sentiment Analysis Through Textual Emotional Descriptions of Visual-Audio Content

Large language models (LLMs) have demonstrated strong capabilities in language understanding and generation, and their potential in educational contexts is increasingly being explored. One promising area is learnersourcing, where students engage in creating their own educational content, such as multiple-choice questions. A critical step in this process is generating effective explanations for the solutions to these questions, as such explanations aid in peer understanding and promote deeper conceptual learning. However, students often find it difficult to craft high-quality explanations due to limited understanding or gaps in their subject knowledge. To support this task, we introduce ``ILearner-LLM,'' a framework that uses iterative enhancement with LLMs to improve generated explanations. The framework combines an explanation generation model and an explanation evaluation model fine-tuned using student preferences for quality, where feedback from the evaluation model is fed back into the generation model to refine the output. Our experiments with LLaMA2-13B and GPT-4 using five large datasets from the PeerWise MCQ platform show that ILearner-LLM produces explanations of higher quality that closely align with those written by students. Our findings represent a promising approach for enriching the learnersourcing experience for students and for leveraging the capabilities of large language models for educational applications.

Exploring Iterative Enhancement for Improving Learnersourced Multiple-Choice Question Explanations with Large Language Models

Assessing students' responses, especially natural language responses, is a major challenge in education. In general, in education contexts, automatically evaluating what learners do or say is important as it enables personalized instruction, e.g., based on what the learner knows tailored tasks and feedback are given to the learner. Recently, deep learning techniques led to state-of-the-art methods in NLP such as transformer-based methods which resulted in significant performance improvements for many NLP tasks such as text classification and question answering. However, there is not much work exploring such methods for assessing students' free answers, particularly in the context of code comprehension, which brings additional challenges as the student explanations include code references as well. This paper explores the potential of applying automated assessments methods using transformers to code comprehension. We fine-tuned pre-trained transformer models, including BERT, RoBERTa, CodeBERT, and SciBERT, to see how well they can automatically judge students' responses to code comprehension tasks. Our results demonstrate that these models can significantly enhance the accuracy and reliability of automated assessments, offering insights into how the latest NLP techniques can be leveraged in computer science education to support personalized learning experiences.

Automated Assessment of Student Self-Explanation in Code Comprehension Using Pre-Trained Language Models

We present a novel Automatic Target Recognition (ATR) system using open-vocabulary object detection and classification models. A primary advantage of this approach is that target classes can be defined just before runtime by a non-technical end user, using either a few natural language text descriptions of the target, or a few image exemplars, or both. Nuances in the desired targets can be expressed in natural language, which is useful for unique targets with little or no training data. We also implemented a novel combination of several techniques to improve performance, such as leveraging the additional information in the sequence of overlapping frames to perform tubelet identification (i.e., sequential bounding box matching), bounding box re-scoring, and tubelet linking. Additionally, we developed a technique to visualize the aggregate output of many overlapping frames as a mosaic of the area scanned during the aerial surveillance or reconnaissance, and a kernel density estimate (or heatmap) of the detected targets. We initially applied this ATR system to the use case of detecting and clearing unexploded ordinance on airfield runways and we are currently extending our research to other real-world applications.

An Application-Agnostic Automatic Target Recognition System Using Vision Language Models

Humans have a strong intuitive understanding of the physical world. Through observations and interactions with the environment, we build mental models that predict how the world would change if we applied a specific action (i.e., intuitive physics). My research draws on these human insights to develop model-based RL agents that learn from their interactions and build predictive models that generalize widely across a range of objects made with different materials. The core idea behind my research is to introduce novel representations and integrate structural priors into learning systems to model dynamics at different levels of abstraction. I will discuss how such structures can make model-based planning algorithms more effective, helping robots accomplish complex manipulation tasks (e.g., manipulating an object pile, shaping deformable foam into a target configuration, and making a dumpling from dough using various tools).

Learning Structured World Models From and For Physical Interactions

Language is highly structured, with syntactic and semantic structures, to some extent, agreed upon by speakers. With implicit or explicit awareness of such structures, humans can learn and use language efficiently and generalize to sentences that contain unseen words. Motivated by human language learning, in this presentation, I will introduce a family of machine learning tasks that learns language structures through grounding, where distant supervision from other data sources (i.e., grounds), including but not limited to different modalities (e.g., vision), execution results of programs, and other languages, are used to guide the learning of language structures. I will demonstrate the potential of this task formulation, advocate for its adoption through three schemes, and discuss the possibility of the general language learning problem through grounding.

Downloads

Next from AAAI 2025

Scaling Combinatorial Optimization Neural Improvement Heuristics with Online Search and Adaptation

Similar lecture

Bridging External and Parametric Knowledge: Mitigating Hallucination of LLMs with Shared-Private Semantic Synergy in Dual-Stream Knowledge