Singapore

Generating with citations is crucial for trustworthy Large Language Models (LLMs), yet even advanced LLMs often produce mismatched or irrelevant citations. Existing methods over-optimize citation fidelity while overlooking relevance to the user query, which degrades answer quality and robustness in real-world settings with noisy or irrelevant retrieved content. Moreover, the prevailing single-pass paradigm struggles to deliver optimal answers in long-form generation that requiring multiple citations. To address these limitations, we propose FineRef, a framework based on Fine-grained error Reflection, which explicitly teaches the model to self-identify and correct two key citation errors—mismatch and irrelevance—on a per-citation basis. FineRef follows a two-stage training strategy. The first stage instills an “attempt–reflect–correct” behavioral pattern via supervised fine-tuning, using fine-grained and controllable reflection data constructed by specialized lightweight models. An online self-reflective bootstrapping strategy is designed to improve generalization by iteratively enriching training data with verified, self-improving examples. To further enhance the self-reflection and correction capability, the second stage applies process-level reinforcement learning with a multi-dimensional reward scheme that promotes reflection accuracy, answer quality, and correction gain. Experiments on the ALCE benchmark demonstrate that FineRef significantly improves both citation performance and answer accuracy. Our 7B model outperforms GPT-4 by up to 18\% in Citation F1 and 4\% in EM Recall, while also surpassing the state-of-the-art model across key evaluation metrics. FineRef also exhibits strong generalization and robustness in domain transfer settings and noisy retrieval scenarios.

AAAI 2026

FineRef: Fine-Grained Error Reflection and Correction for Long-Form Generation with Citations

long-form generation with citations

self-correction

self-reflection

### Welcome!
The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024) will take place in Bangkok, Thailand from August 11th to 16th, 2024. Our Virtual Poster Sessions will take place online Thursday, August 22, 2024.

You are required to register for this event. **Please register [here](https://2024.aclweb.org/registration). **

If you have already registered, please check your inbox for an email from Underline granting you access to ACL 2024 content.

Please register!

ACL 2024

The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024) will take place in Bangkok, Thailand from August 11th to 16th, 2024. More information will be announced soon.

technical paper

We are pleased to announce the Fortieth AAAI Conference on Artificial Intelligence (AAAI-26), which will be held in Singapore EXPO from January 20 to January 27, 2026.

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-26 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.

To access this event page, you need to log in with the **email address you registered with**. Access credentials will be sent to your email from Underline - subject line "Welcome to AAAI 2026". Please be sure to check your spam email folder if you do not see an email confirmation right away.

Please log in

To access this event page, you are required to register.
Please complete your registration to continue.

We recommend reading [**the registration information**](https://aaai.org/conference/aaai/aaai-26/registration/) first.

**Online Registration Form**: https://aaai.getregistered.net/conference-2026 

Registration Required

We are pleased to announce the Fortieth AAAI Conference on Artificial Intelligence (AAAI-26), which will be held in Singapore EXPO from January 20 to January 27, 2026.

Our world is constantly evolving, and human beings
continuously enhance their knowledge by learning from their
experiences throughout life. Despite significant
advancements in embodied AI, current agents struggle to
operate reliably, robustly, and continually in complex,
real-world multimodal environments due to complex problems
that span large and diverse domains, especially when faced
with out-of-distribution (OOD) scenarios they have not
previously encountered. Our goal is to develop a
multimodal, embodied AI system that continually enhances
its capabilities and skills through safe and robust
interactions with an ever-changing, multimodal world. This
is enabled by a novel, adaptively expandable memory
architecture that integrates both long- and short-term
information across multiple modalities. The system
selectively decides what to store and learn, filtering out
adversarial or low-quality inputs to prevent negative
transfer and distractions, while improving overall
efficiency and effectiveness.

Towards Continually-Evolving Multimodal Embodied AI: Selective and Expandable Multimodal Memory System

Rice cultivation supplies half the world's population with staple food, while also being a major driver of freshwater depletion—consuming roughly a quarter of global freshwater—and accounting for $\sim$48\% of greenhouse gas emissions from croplands. In regions like Punjab, India, where groundwater levels are plummeting at 41.6 cm/year, adopting water-saving rice farming practices is critical. Direct-Seeded Rice (DSR) and Alternate Wetting and Drying (AWD) can cut irrigation water use by 20–40\% without hurting yields, yet lack of spatial data on adoption impedes effective adaptation policy and climate action. We present a machine learning framework to bridge this data gap by monitoring sustainable rice farming at scale. In collaboration with agronomy experts and a large-scale farmer training program, we obtained ground-truth data from $\sim$1,400 fields across Punjab. Leveraging this partnership, we developed a novel dimensional classification approach that decouples sowing and irrigation practices, achieving F1 scores of 0.772 and 0.806 respectively, solely employing Sentinel-1 satellite imagery. Explainability analysis reveals that DSR classification is reliable while AWD classification depends primarily on planting schedule differences, as Sentinel-1's 12-day revisit frequency cannot capture the higher frequency irrigation cycles characteristic of AWD practices. Applying this model across 3 million fields reveals spatial inequities in adoption at the state level, highlighting gaps and opportunities for policy targeting. Our district-level adoption rates correlate strongly (Pearson=0.87) with government estimates. This study provides policymakers and sustainability programs a powerful tool to track practice adoption, inform targeted interventions, and drive data-driven policies for water conservation and climate mitigation at regional scale. We release all code and models at: \url{https://github.com/anonymous-repo} to support reproducibility and future research.

Machine Learning for Sustainable Rice Production: Region-Scale Monitoring of Water-Saving Practices in Punjab, India

As AI technologies grow more influential in shaping modern
life, there is an urgent need to make AI literacy
accessible beyond academic and technical communities. This
paper presents the design, delivery, and evaluation of an
online AI course targeting the general public. The course
combined asynchronous lectures, interactive live sessions,
and reflective assignments. Of the 343 people who
registered, 169 completed the program. Using validated
instruments administered before and after the course, we
measured changes in participants’ attitudes toward AI and
their AI literacy. Our findings revealed statistically
significant changes in AI literacy, specifically in
awareness, usage, and evaluation constructs, as well as a
rise in positive attitudes toward AI. High satisfaction
scores and qualitative feedback further support the
course’s effectiveness. These findings reinforce the
importance of inclusive, scalable educational interventions
for empowering the public to navigate AI technologies.

Educating the Public in Artificial Intelligence: Insights from a Large-Scale Course

Exploring how genetic sequences shape phenotypes is a fundamental challenge in biology and a key step toward scalable, hypothesis-driven experimentation. The task is complicated by the large modality gap between sequences and phenotypes, as well as the pleiotropic nature of gene–phenotype relationships. Existing sequence-based efforts focus on the degree to which variants of specific genes alter a limited set of phenotypes, while general gene knockout-induced phenotype abnormality prediction methods heavily rely on curated genetic information as inputs, which limits scalability and generalizability. As a result, the task of broadly predicting the presence of multiple phenotype abnormalities under gene knockout directly from gene sequences remains underexplored. We introduce GenePheno, the first interpretable multi-label prediction framework that predicts knockout-induced phenotypic abnormalities from gene sequences. GenePheno employs a contrastive multi-label learning objective that captures inter-phenotype correlations, complemented by an exclusive regularization that enforces biological consistency. It further incorporates a gene function bottleneck layer, offering human-interpretable concepts that reflect functional mechanisms behind phenotype formation. To support progress in this area, we curate four datasets with canonical gene sequences as input and multi-label phenotypic abnormalities induced by gene knockouts as targets. Across these datasets, GenePheno achieves state-of-the-art gene-centric $F_{max}$ and phenotype-centric AUC, and case studies demonstrate its ability to reveal gene functional mechanisms.

GenePheno: Interpretable Gene Knockout-Induced Phenotype Abnormality Prediction from Gene Sequences

Hierarchical goal networks (HGNs) provide a framework for goal-directed planning by decomposing high-level goals into ordered subgoals. While prior work has examined non-determinism for hierarchical planning (specifically, HTNs), scant work studies how HGNs can help in stochastic settings. We introduce a formalism for probabilistic HGN planning with task-insertion semantics, enabling probabilistic planners to incorporate domain knowledge from goal decomposition methods. We design and evaluate two UCT-based algorithms for solving probabilistic HGN planning problems: an asymptotically optimal approach and a "tree-compression" approach that optimizes separately for the goals within the goal-subgoal hierarchy. We compare our two UCT-based HGN search algorithms experimentally on modified benchmark domains from the FOND-HTN literature. Our results demonstrate that on larger problems, the compressed search converges more quickly and outperforms the asymptotically optimal search. This suggests that HGNs can be effective in probabilistic planning and tree compression may yield better performance on large problems in anytime settings with stochastic action outcomes.

Probabilistic Hierarchical Goal Network Planning with UCT

Accurate multi-turn intent classification is essential for advancing conversational AI systems. Yet, it remains challenging due to the scarcity of comprehensive datasets and the complexity of contextual dependencies across dialogue turns hinder progress. This paper presents two novel approaches leveraging Large Language Models (LLMs) to enhance scalability and reduce latency in production dialogue systems. First, we introduce Symbol Tuning, which simplifies intent labels to reduce task complexity and improve performance in multi-turn dialogues. Second, we propose C-LARA (Consistency-aware, Linguistics Adaptive Retrieval Augmentation), a framework that employs LLMs for data augmentation and pseudo-labeling to generate synthetic multi-turn dialogues. These enriched datasets are used to fine-tune a small, efficient model suitable for deployment. Experiments conducted on multilingual dialogue datasets demonstrate significant improvements in classification accuracy and resource efficiency. Our methods enhance multi-turn intent classification accuracy by 5.09%, reduce annotation costs by 40%, and enable scalable deployment in low-resource multilingual industrial systems, highlighting their practicality and impact.

Balancing Accuracy and Efficiency in Multi-Turn Intent Classification for LLM-Powered Dialog Systems in Production

This paper proposes DeepSynth, a method for effective training of deep reinforcement learning agents when the reward is sparse or non-Markovian, but at the same time progress towards the reward requires achieving an unknown sequence of high-level objectives. Our method employs a novel algorithm for synthesis of compact finite state automata to uncover this sequential structure automatically. We synthesise a human-interpretable automaton from trace data collected by exploring the environment. The state space of the environment is then enriched with the synthesised automaton, so that the generation of a control policy by deep reinforcement learning is guided by the discovered structure encoded in the automaton. The proposed approach is able to cope with both high-dimensional, low-level features and unknown sparse or non-Markovian rewards. We have evaluated DeepSynth’s performance in a set of experiments that includes the Atari game Montezuma’s Revenge, known to be challenging. Compared to approaches that rely solely on deep reinforcement learning, we obtain a reduction of two orders of magnitude in the iterations required for policy synthesis, and a significant improvement in scalability.

Symbolic Task Inference in Deep Reinforcement Learning

Large language models have revolutionized textual reasoning, yet their ability to act meaningfully in multimodal, real-world environments remains limited. They struggle to ground their decisions in visual context, adapt to changing goals, and plan actions over time—shortcomings that stem from a lack of structured, goal-driven reasoning and insufficient representations of the physical world.

In this talk, I present a unified framework for building embodied agents that can see, simulate, and reason. I begin by introducing methods for learning world simulators from data, arguing that visual reasoning—like textual reasoning—benefits from step-by-step processing. Inverting a physics simulator becomes key: agents must infer structured 3D neural representations of objects, parts, motions, and scenes directly from raw video. I describe methods for extracting such representations using generative priors, injecting them into vision-language models (VLMs), and scaling up their supervision via generative 3D simulation and fast, modular physics engines. These simulators enable agents to anchor their predictions in grounded physical reality, reducing hallucinations and improving control.

Complementing this simulation capability, I explore techniques that enable agents to reason over time and adapt their behavior. By integrating structured memory systems, agents learn to retain and retrieve relevant experiences to inform long-horizon plans. Language-based reflective feedback allows them to refine their strategies beyond what sparse rewards offer, forming abstractions that generalize across tasks. When trained to ground their reasoning directly in the visual environment, agents gain the ability to set subgoals, explore effectively, and verify their own hypotheses.

Together, these advances point toward autonomous systems that simulate before they act, reflect after they fail, and maintain an ongoing awareness of goals, constraints, and context. I will illustrate these capabilities across web automation, robotics, and interactive assistance, showing how agents that see, simulate, and reason offer a promising path toward general-purpose embodied intelligence.

Towards Embodied Agents that See, Simulate, and Reason

AI and Program Reviewing Panel

Over the past few years, Artificial Intelligence has bounded into the mainstream of society.  Remarkable technical achievements in the use of Deep Learning and  Large Language Models have given rise to expectations and hype regarding the possibility of achieving artificial general intelligence, as well as general concerns over the potential deleterious consequences of emerging AI technologies and how to ensure their responsible use. In this panel we engage four Past AAAI Presidents to discuss their views on questions relating to the current state and future of AI research, including such topics as important emerging application areas, current technical challenges, the eventual prospects for achieving artificial general intelligence, and potential AI risks and solutions.

Content not yet available

Downloads

Next from AAAI 2026

Towards Continually-Evolving Multimodal Embodied AI: Selective and Expandable Multimodal Memory System

Similar lecture

Learning to Generate Answers with Citations via Factual Consistency Models

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Content not yet available

.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 2026

Towards Continually-Evolving Multimodal Embodied AI: Selective and Expandable Multimodal Memory System

Similar lecture

Learning to Generate Answers with Citations via Factual Consistency Models

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads