Papers by Ben Liu

21 papers
MSEarth: A Multimodal Benchmark for Earth Science Phenomenon Discovery with MLLMs (2026.acl-long)

Copied to clipboard

Challenge: Existing datasets often rely on synthetic data or figure-caption pairs, failing to capture the depth and complexity of geoscientific reasoning.
Approach: They propose a multimodal scientific dataset and benchmark curated from open-access publications.
Outcome: MSEarth features over 289K figures with captions enriched by contextual discussions and reasoning from original papers.
Towards Explainable Temporal Reasoning in Large Language Models: A Structure-Aware Generative Framework (2025.findings-acl)

Copied to clipboard

Challenge: Existing studies on temporal reasoning models neglect the explainable reasoning processes underlying the results.
Approach: They propose a structure-aware generative framework that integrates Graph structures with text for Explainable TEmporal Reasoning.
Outcome: The proposed framework achieves state-of-the-art performance while also demonstrating robust generalization capabilities.
SMiLE: Schema-augmented Multi-level Contrastive Learning for Knowledge Graph Link Prediction (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for linking knowledge graphs lack contextual information in entity neighborhoods, which leads to false prediction results.
Approach: They propose a Schema-augmented Multi-level contrastive LEarning framework to conduct knowledge graph link prediction using a knowledge graph schema.
Outcome: The proposed framework is based on a knowledge graph schema and is compared against state-of-the-art datasets.
Familiarity-Aware Evidence Compression for Retrieval-Augmented Generation (2025.findings-emnlp)

Copied to clipboard

Challenge: Retrieval-augmented generation (RAG) improves large language models by incorporating non-parametric knowledge through evidence retrieved from external sources.
Approach: They propose a training-free evidence compression technique that makes retrieved evidence more familiar to the target model while seamlessly integrating parametric knowledge from the model.
Outcome: The proposed technique outperforms the most recent evidence compression baselines across open-domain QA datasets while achieving high compression rates.
Deja vu: Contrastive Historical Modeling with Prefix-tuning for Temporal Knowledge Graph Reasoning (2024.findings-naacl)

Copied to clipboard

Challenge: Existing text-based methods for Temporal Knowledge Graph Reasoning struggle to balance textual knowledge and temporal information with expensive purpose-built training strategies.
Approach: They propose a Contrastive historical modeling framework with prefix-tuning for TEmporal Reasoning that feeds history-contextualized text into the pseudo-Siamese encoders to strike a textual-temporal balance.
Outcome: The proposed framework achieves superior performance on four transductive and three few-shot inductive TKGR benchmarks.
Navigating the Infinite Dynamic Web Space: Effective In-Context Exploration via Cognitive Multi-Agent Collaboration (2026.eacl-long)

Copied to clipboard

Challenge: Existing methods for dynamic web navigation rely on greedy strategies or value estimation, struggle to achieve effective backtracking and are heavily dependent on proprietary models.
Approach: They propose a cognitive multi-agent collaboration framework that enhances cyberspace exploration capability through In-Context Exploration.
Outcome: The proposed framework surpasses the proprietary model Claude-3.5 Sonnet on the WebArena benchmark.
Reliable Use of Lemmas via Eligibility Reasoning and Section-Aware Reinforcement Learning (2026.acl-short)

Copied to clipboard

Challenge: Recent large language models (LLMs) perform strongly on mathematical benchmarks but often import conclusions without validating assumptions.
Approach: They propose a model that encodes a lemma specification and trains with reinforcement learning and section-aware loss masking to assign penalty to the section responsible for errors.
Outcome: The proposed model performs well on benchmarks but often misapplyes lemmas . the model is able to encode the specification and train with reinforcement learning .
ResearchBench: Benchmarking LLMs in Scientific Discovery via Inspiration-Based Task Decomposition (2026.findings-acl)

Copied to clipboard

Challenge: Large language models have shown potential in assisting scientific research, yet their ability to discover high-quality research hypotheses remains unexamined due to the lack of a dedicated benchmark.
Approach: They propose a benchmark for evaluating large language models on a sufficient set of scientific discovery sub-tasks.
Outcome: The proposed framework extracts critical components from papers across 12 disciplines with expert validation confirming its accuracy.
XMC-Agent : Dynamic Navigation over Scalable Hierarchical Index for Incremental Extreme Multi-label Classification (2024.findings-acl)

Copied to clipboard

Challenge: Existing methods for XMC struggle with the growing set of labels due to their static label assumptions, and embedding-based methods struggle with complex mapping relationships due to late interaction paradigm.
Approach: They propose a large language model (LLM) powered agent framework for extreme multi-label classification, XMC-Agent, which can effectively learn, manage and predict the extremely large and dynamically increasing set of labels.
Outcome: The proposed framework can learn, manage and predict the extremely large and dynamically growing set of labels and achieves state-of-the-art performance on three standard datasets.
OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis (2025.acl-long)

Copied to clipboard

Challenge: Graphical User Interface (GUI) agents powered by Vision-Language Models (VLMs) have demonstrated human-like computer control capability.
Approach: They propose a GUI data synthesis pipeline that reverse engineers GUI trajectory construction process by executing pre-defined tasks.
Outcome: The proposed GUI data synthesis pipeline overcomes the bottlenecks of previous methods that rely on pre-defined tasks and limited data diversity.
Perturbed Masking: Parameter-free Probing for Analyzing and Interpreting BERT (2020.acl-main)

Copied to clipboard

Challenge: Recent pre-trained language models achieve state-of-the-art performance for downstream NLP tasks.
Approach: They propose a parameter-free probing technique for analyzing pre-trained language models . their method does not require direct supervision from probing tasks .
Outcome: The proposed method improves on linguistically-uninformed baselines on pre-trained language models.
Evaluating Models’ Local Decision Boundaries via Contrast Sets (2020.findings-emnlp)

Copied to clipboard

Challenge: Standard test sets for supervised learning evaluate in-distribution generalization but are misleading when a dataset has systematic gaps.
Approach: They propose a more rigorous annotation paradigm for NLP that helps to close systematic gaps in the test data.
Outcome: The proposed model performs significantly lower on contrast sets than on the original test sets—up to 25% in some cases.
Expanding the Boundaries of Vision Prior Knowledge in Multi-modal Large Language Models (2026.eacl-long)

Copied to clipboard

Challenge: Existing research treats MLLMs as unified systems optimized through end-to-end training, but the impact of vision encoder’s prior knowledge is seldom investigated.
Approach: They propose a metric to quantify the effect of prior knowledge on MLLM performance by integrating prior knowledge at the vision encoder level into a training framework.
Outcome: The proposed training framework incorporates prior knowledge at the vision encoder level, and significantly boosts visual understanding capabilities of MLLMs.
OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic Workflows (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for detecting unsafe mobile GUI agents are underexplored.
Approach: They propose a mobile agent safety detection framework that integrates a formal verifier and a VLM-based contextual judge to detect system-level violations.
Outcome: The proposed framework achieves 10%–30% improvements over existing approaches across multiple metrics.
Pre-trained Language Model with Prompts for Temporal Knowledge Graph Completion (2023.findings-acl)

Copied to clipboard

Challenge: Existing methods for temporal knowledge graph completion (TKGC) focus on extracting information from timestamps and insufficiently utilizing implied information in relations.
Approach: They propose a temporal knowledge graph completion model with prompts that converts quadruples into pre-trained language inputs and prompts to make coherent sentences with implicit semantic information.
Outcome: The proposed model can make coherent sentences with implicit semantic information.
Towards Enhancing Health Coaching Dialogue in Low-Resource Settings (2022.coling-1)

Copied to clipboard

Challenge: Health coaching is cost-prohibitive due to its highly personalized nature.
Approach: They propose to build a health coaching dialogue system that converses with patients . they propose to use simplified NLU and NLG frameworks and mechanism-conditioned empathetic response generation.
Outcome: The proposed system generates more empathetic, fluent, and coherent responses . it outperforms the state-of-the-art in NLU tasks while requiring less annotations.
Scale Down to Speed Up: Dynamic Data Selection for Reinforcement Learning (2025.findings-emnlp)

Copied to clipboard

Challenge: Current approaches to Reinforcement Learning (RL) rely on massive static datasets, leading to computational inefficiency and redundant gradient updates.
Approach: They propose a data-centric RL framework that dynamically selects the most informative training samples to optimize RL for mathematical reasoning.
Outcome: The proposed framework achieves comparable performance to full-data training methods while requiring only 1.5K samples instead of 220K, reducing training time from 13 days to just 4 hours on 8A800 GPUs.
QA‐LIGN: Aligning LLMs through Constitutionally Decomposed QA (2025.findings-emnlp)

Copied to clipboard

Challenge: QA-LIGN decomposes monolithic rewards into interpretable principle-specific evaluations . scalar rewards obscure which objectives drive the training signal .
Approach: a new method decomposes monolithic rewards into interpretable principle-specific evaluations . QA-LIGN reduces attack success rates by up to 68.7% while maintaining a 0.67% false refusal rate .
Outcome: QA-LIGN reduces attack success rates by up to 68.7% while maintaining a 0.67% false refusal rate . the results outperform DPO and GRPO with state-of-the-art reward models given equivalent training .
Filter-then-Generate: Large Language Models with Structure-Text Adapter for Knowledge Graph Completion (2025.coling-main)

Copied to clipboard

Challenge: Empirical evidence suggests that LLMs perform worse than conventional KGC approaches.
Approach: They propose a filter-then-generate paradigm and a multiple-choice question format to harness the capability of LLMs while mitigating the issue casused by hallucinations.
Outcome: The proposed method achieves substantial performance gain compared to existing state-of-the-art methods.
Understanding Differential Search Index for Text Retrieval (2023.findings-acl)

Copied to clipboard

Challenge: Differentiable Search Index (DSI) is a new information retrieval framework . however, due to the black-box nature of the end-to-end neural architecture, it remains unclear to what extent it possesses basic indexing and retrieval abilities.
Approach: They propose a multi-task distillation approach to enhance the retrieval quality without altering the structure of the model.
Outcome: The proposed method outperforms baselines on various datasets.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations