Charlotte Pouw, Hosein Mohebbi, Afra Alishahi, Willem Zuidema · Apr 7, 2026 · Citations: 0
Demonstrations General
← Back to explorer In-Context Learning in Speech Language Models: Analyzing the Role of Acoustic Features, Linguistic Structure, and Induction Heads MMEmb-R1: Reasoning-Enhanced Multimodal Embedding with Pair-Aware Selection and Adaptive Control Social Dynamics as Critical Vulnerabilities that Undermine Objective Decision-Making in LLM Collectives FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks Beyond Paper-to-Paper: Structured Profiling and Rubric Scoring for Paper-Reviewer Matching Evaluating Learner Representations for Differentiation Prior to Instructional Outcomes Controlling Distributional Bias in Multi-Round LLM Generation via KL-Optimized Fine-Tuning Label Effects: Shared Heuristic Reliance in Trust Assessment by Humans and LLM-as-a-Judge Weakly Supervised Distillation of Hallucination Signals into Transformer Representations MemMachine: A Ground-Truth-Preserving Memory System for Personalized AI Agents Strengthening Human-Centric Chain-of-Thought Reasoning Integrity in LLMs via a Structured Prompt Framework Full-Duplex-Bench-v3: Benchmarking Tool Use for Full-Duplex Voice Agents Under Real-World Disfluency Selecting Decision-Relevant Concepts in Reinforcement Learning JoyAI-LLM Flash: Advancing Mid-Scale LLMs with Token Efficiency ActionParty: Multi-Subject Action Binding in Generative Video Games Novel Memory Forgetting Techniques for Autonomous AI Agents: Balancing Relevance and Efficiency LEO: Graph Attention Network based Hybrid Multi Sensor Extended Object Fusion and Tracking for Autonomous Driving Applications Brief Is Better: Non-Monotonic Chain-of-Thought Budget Effects in Function-Calling Language Agents SEAL: An Open, Auditable, and Fair Data Generation Framework for AI-Native 6G Networks LLM-as-a-Judge for Time Series Explanations
Tag: General
General papers in the current HFEPX explorer (897 papers).
Papers in tag: 897
Running a General study?
Post a Job →Research Utility Snapshot
Evaluation Modes
- Automatic Metrics (13)
- Llm As Judge (3)
- Simulation Env (3)
Human Feedback Types
- Pairwise Preference (5)
- Rubric Rating (2)
- Demonstrations (1)
Required Expertise
- General (20)
Yuchi Wang, Dingkang Yang, Haiyang Yu, Weikang Bian, Jiefeng Long, Xiao Liang · Apr 7, 2026 · Citations: 0
Pairwise Preference Automatic Metrics General
- Experiments on the MMEB-V2 benchmark demonstrate that our model achieves a score of 71.2 with only 4B parameters, establishing a new state-of-the-art while significantly reducing reasoning overhead and inference latency.
Changgeon Ko, Jisu Shin, Hoyun Song, Huije Lee, Eui Jun Hwang, Jong C. Park · Apr 7, 2026 · Citations: 0
Automatic MetricsSimulation Env General
- Large language model (LLM) agents are increasingly acting as human delegates in multi-agent environments, where a representative agent integrates diverse peer perspectives to make a final decision.
- Our experiments demonstrate that the representative agent's accuracy consistently declines as social pressure increases: larger adversarial groups, more capable peers, and longer arguments all lead to significant performance degradation.
Michael Krumdick, Varshini Reddy, Shivani Chaudhary, William Day, Maarij Ahmed, Hayan Haqqi · Apr 7, 2026 · Citations: 0
Rubric Rating General
- To address this, we introduce FrontierFinance, a long-horizon benchmark of 25 complex financial modeling tasks across five core finance models, requiring an average of over 18 hours of skilled human labor per task to complete.
- We demonstrate that our human experts both receive higher scores on average, and are more likely to provide client-ready outputs than current state-of-the-art systems.
Yicheng Pan, Zhiyuan Ning, Ludi Wang, Yi Du · Apr 7, 2026 · Citations: 0
Rubric Rating Automatic Metrics General
Junsoo Park, Youssef Medhat, Htet Phyo Wai, Ploy Thajchayapong, Ashok K. Goel · Apr 7, 2026 · Citations: 0
Pairwise Preference General
- We introduce distinctiveness, a representation-level measure that evaluates how each learner differs from others in the cohort using pairwise distances, without requiring clustering, labels, or task-specific evaluation.
- Using student-authored questions collected through a conversational AI agent in an online learning environment, we compare representations based on individual questions with representations that aggregate patterns across a student's…
Yanbei Jiang, Amr Keleg, Ryandito Diandaru, Jey Han Lau, Lea Frermann, Biaoyan Fang · Apr 7, 2026 · Citations: 0
Pairwise Preference General
- Our empirical analysis reveals that off-the-shelf LLMs and standard alignment techniques, including prompt engineering and Direct Preference Optimization, fail to reliably control output distributions.
Xin Sun, Di Wu, Sijing Qin, Isao Echizen, Abdallah El Ali, Saku Sugawara · Apr 7, 2026 · Citations: 0
Pairwise Preference Llm As Judge General
- Large language models (LLMs) are increasingly used as automated evaluators (LLM-as-a-Judge).
- Using a counterfactual design, we find that both humans and LLM judges assign higher trust to information labeled as human-authored than to the same content labeled as AI-generated.
Shoaib Sadiq Salehmohamed, Jinal Prashant Thakkar, Hansika Aredla, Shaik Mohammed Omar, Shalmali Ayachit · Apr 7, 2026 · Citations: 0
Llm As JudgeAutomatic Metrics General
- We introduce a weak supervision framework that combines three complementary grounding signals: substring matching, sentence embedding similarity, and an LLM as a judge verdict to label generated responses as grounded or hallucinated without…
- Transformer-based probes achieve the strongest discrimination, with M2 performing best on 5-fold average AUC/F1, and M3 performing best on both single-fold validation and held-out test evaluation.
Shu Wang, Edwin Yu, Oscar Love, Tom Zhang, Tom Wong, Steve Scargall · Apr 6, 2026 · Citations: 0
Automatic Metrics General
- Large Language Model (LLM) agents require persistent memory to maintain personalization, factual continuity, and long-horizon reasoning, yet standard context-window and retrieval-augmented generation (RAG) pipelines degrade over…
- Across benchmarks, MemMachine achieves strong accuracy-efficiency tradeoffs: on LoCoMo it reaches 0.9169 using gpt4.1-mini; on LongMemEvalS (ICLR 2025), a six-dimension ablation yields 93.0 percent accuracy, with retrieval-stage…
Jiling Zhou, Aisvarya Adeseye, Seppo Virtanen, Antti Hakkala, Jouni Isoaho · Apr 6, 2026 · Citations: 0
Human EvalAutomatic Metrics General
- However, its reliability in security-sensitive analytical tasks remains insufficiently examined, particularly under structured human evaluation.
- Human evaluation with strong inter-rater agreement (Cohen's k > 0.80) confirms robustness.
Guan-Ting Lin, Chen Chen, Zhehuai Chen, Hung-yi Lee · Apr 6, 2026 · Citations: 0
Automatic Metrics General
- We introduce Full-Duplex-Bench-v3 (FDB-v3), a benchmark for evaluating spoken language models under naturalistic speech conditions and multi-step tool use.
- Unlike prior work, our dataset consists entirely of real human audio annotated for five disfluency categories, paired with scenarios requiring chained API calls across four task domains.
Naveen Raman, Stephanie Milani, Fei Fang · Apr 6, 2026 · Citations: 0
Expert Verification General
- Training interpretable concept-based policies requires practitioners to manually select which human-understandable concepts an agent should reason with when making sequential decisions.
- Our key insight is that concept selection can be viewed through the lens of state abstraction: intuitively, a concept is decision-relevant if removing it would cause the agent to confuse states that require different actions.
Aichen Cai, Anmeng Zhang, Anyu Li, Bo Zhang, Bohua Cai, Chang Li · Apr 3, 2026 · Citations: 0
Pairwise Preference General
- JoyAI-LLM Flash is pretrained on a massive corpus of 20 trillion tokens and further optimized through a rigorous post-training pipeline, including supervised fine-tuning (SFT), Direct Preference Optimization (DPO), and large-scale…
Alexander Pondaven, Ziyi Wu, Igor Gilitschenski, Philip Torr, Sergey Tulyakov, Fabio Pizzati · Apr 2, 2026 · Citations: 0
Automatic MetricsSimulation Env General
- However, these models are largely restricted to single-agent settings, failing to control multiple agents simultaneously in a scene.
- We evaluate ActionParty on the Melting Pot benchmark, demonstrating the first video world model capable of controlling up to seven players simultaneously across 46 diverse environments.
Payal Fofadiya, Sunil Tiwari · Apr 2, 2026 · Citations: 0
Automatic Metrics General
- Long-horizon conversational agents require persistent memory for coherent reasoning, yet uncontrolled accumulation causes temporal decay and false memory propagation.
- Benchmarks such as LOCOMO and LOCCO report performance degradation from 0.455 to 0.05 across stages, while MultiWOZ shows 78.2% accuracy with 6.8% false memory rate under persistent retention.
Mayank Mayank, Bharanidhar Duraisamy, Florian Geiss · Apr 2, 2026 · Citations: 0
Automatic Metrics General
- Evaluations on the Mercedes-Benz DRIVE PILOT SAE L3 dataset demonstrate real-time computational efficiency suitable for production systems; additional validation on public datasets such as View of Delft (VoD) further confirms cross-dataset…
Xuan Qi · Apr 2, 2026 · Citations: 0
Automatic Metrics General
- Chain-of-thought (CoT) reasoning is widely assumed to improve agent performance, but the relationship between reasoning length and accuracy in structured tool-use settings remains poorly understood.
- We present a systematic study of CoT budget effects on function-calling agents, sweeping six token budgets (0--512) across 200 tasks from the Berkeley Function Calling Leaderboard v3 Multiple benchmark.
Sunder Ali Khowaja, Kapal Dev, Engin Zeydan, Madhusanka Liyanage · Apr 2, 2026 · Citations: 0
Automatic MetricsSimulation Env General
Preetham Sivalingam, Murari Mandal, Saurabh Deshpande, Dhruv Kumar · Apr 2, 2026 · Citations: 0
Llm As JudgeAutomatic Metrics General
- Although modern models generate textual interpretations of numerical signals, existing evaluation methods are limited: reference based similarity metrics and consistency checking models require ground truth explanations, while traditional…
- To support this, we construct a synthetic benchmark of 350 time series cases across seven query types, each paired with correct, partially correct, and incorrect explanations.