12 citations · 36 across the 32 of their papers we have counts for
36 papers
SWE-VERIFIER: Selective Verification for Cost-Efficient Coding Agents
Kaijian Zou, Vaibhav Chennareddy, Yunxiang Zhang +5
Coding agents spend substantial computation generating actions and processing long interaction histories. Poor action choices can steer agents into low-value states, wasting comput…
REMORY: Learning Residual Memory for Context Compaction
Hanchen Xia, Baoyou Chen, Yutang Ge +5
Long-horizon agents compact their history to continue within a finite context window, but a textual summary alone may not support every subsequent decision. We introduce REMORY, a…
Retrieval-Based In-Context Learning: A Domain Adaptation Framework
Yilun Zhu, Naihao Deng, Yingcong Li +2
In-context retrieval (ICR) is a retrieval-based form of in-context learning (ICL) in which demonstrations are retrieved from a source database based on similarity to the query, rat…
LLaDA-PRM: A Bidirectional Step-Level Reasoning Evaluator
Yiming Feng, Naihao Deng, Yulong Chen +1
Step-level reasoning evaluators are commonly based on autoregressive language models, whose causal attention restricts each step representation to the problem, previous steps, and…
One Example Is Enough to Pass Fairness Benchmarks: Rethinking Fairness Evaluation for Aligned LLMs
Naihao Deng, Samee Arif, Shuaichen Chang +2
Warning: This submission studies stereotypes and biases, and contains toxic and offensive examples, used for illustration purposes only. Fairness benchmarks such as BBQ have become…
AtlasNLP: A Country-Aware Atlas of Dataset Representation in NLP
Joan Nwatu, Tsedeniya Solomon Amare, Longju Bai +17
Understanding which countries are represented in NLP datasets is essential for identifying gaps, targeting data collection, measuring progress, and informing AI policy. However, ge…
It Takes One to Bias Them All: Breaking Bad with One-Shot GRPO
Naihao Deng, Yilun Zhu, Naichen Shi +2
Warning: This paper contains several toxic and offensive statements. Modern large language models (LLMs) are typically aligned through large-scale post-training to ensure fair and…
Wait, am I Being Fair? Characterizing Deductive Stereotyping and Mitigating It with Fair-GCG
Naihao Deng, Yilun Zhu, Joan Nwatu +2
Warning: This paper contains several toxic and offensive statements. While reasoning generally improves fairness in recent large language models (LLMs), failures persist. In this w…
The Language-Energy Divide: Measuring Energy Costs of Multilingual LLM Inference
Naihao Deng, Alissa Shen, Yiming Feng +5
Large language models (LLMs) are increasingly deployed in multilingual settings, yet the energy costs of serving these models across different languages remain poorly understood. W…
The Wrong Kind of Right: Quantifying and Localizing Misfired Alignment in LLMs
Naihao Deng, Yiming Feng, Chimaobi Okite +4
Warning: This paper studies stereotypes and biases, and contains potentially disturbing examples, used for illustration purposes only. Our findings should not be interpreted as an…
SafetyALFRED: Evaluating Safety-Conscious Planning of Multimodal Large Language Models
Josue Torres-Fonseca, Naihao Deng, Yinpei Dai +5
Multimodal Large Language Models are increasingly adopted as autonomous agents in interactive environments, yet their ability to proactively address safety hazards remains insuffic…
DOTRAG: Retrieval-Time Reasoning Along Paths
Larnell Moore, Naihao Deng, Rada Mihalcea +1
Graph Retrieval-Augmented Generation (GraphRAG) is dominated by a retrieve-then-reason paradigm, where context is retrieved using heuristics and then reasoned over. Such methods st…
Beyond Screenshots: Evaluating VLMs' Understanding of UI Animations
Chen Liang, Xirui Jiang, Naihao Deng +2
AI agents operating on user interfaces must understand how interfaces communicate state and feedback to act reliably. As a core communicative modality, animations are increasingly…
One Word at a Time: Incremental Completion Decomposition Breaks LLM Safety
Samee Arif, Naihao Deng, Zhijing Jin +1
Large Language Models (LLMs) are trained to refuse harmful requests, yet they remain vulnerable to jailbreak attacks that exploit weaknesses in conversational safety mechanisms. We…
Domain Generalization Under Posterior Drift
Yilun Zhu, Naihao Deng, Naichen Shi +2
Domain generalization (DG) is the problem of generalizing from several distributions (or domains), for which labeled training data are available, to a new test domain for which no…
Benchmarking and Improving LLM Robustness for Personalized Generation
Chimaobi Okite, Naihao Deng, Kiran Bodipati +3
Recent years have witnessed a growing interest in personalizing the responses of large language models (LLMs). While existing evaluations primarily focus on whether a response alig…
CliniDial: A Naturally Occurring Multimodal Dialogue Dataset for Team Reflection in Action During Clinical Operation
Naihao Deng, Kapotaksha Das, Rada Mihalcea +2
In clinical operations, teamwork can be the crucial factor that determines the final outcome. Prior studies have shown that sufficient collaboration is the key factor that determin…
Are Human Interactions Replicable by Generative Agents? A Case Study on Pronoun Usage in Hierarchical Interactions
Naihao Deng, Rada Mihalcea
As Large Language Models (LLMs) advance in their capabilities, researchers have increasingly employed them for social simulation. In this paper, we investigate whether interactions…
Table as Thought: Exploring Structured Thoughts in LLM Reasoning
Zhenjie Sun, Naihao Deng, Haofei Yu +1
Large language models' reasoning abilities benefit from methods that organize their thought processes, such as chain-of-thought prompting, which employs a sequential structure to g…
What Really Matters for Table LLMs? A Meta-Evaluation of Model and Data Effects
Naihao Deng, Sheng Zhang, Henghui Zhu +7
Table modeling has progressed for decades. In this work, we revisit this trajectory and highlight emerging challenges in the LLM era, particularly the paradox of choice: the diffic…
Rethinking Table Instruction Tuning
Naihao Deng, Rada Mihalcea
Recent advances in table understanding have focused on instruction-tuning large language models (LLMs) for table-related tasks. However, existing research has overlooked the impact…
Chumor 2.0: Towards Benchmarking Chinese Humor Understanding
Ruiqi He, Yushu He, Longju Bai +7
Existing humor datasets and evaluations predominantly focus on English, leaving limited resources for culturally nuanced humor in non-English languages like Chinese. To address thi…
Chumor 1.0: A Truly Funny and Challenging Chinese Humor Understanding Dataset from Ruo Zhi Ba
Ruiqi He, Yushu He, Longju Bai +6
Existing humor datasets and evaluations predominantly focus on English, lacking resources for culturally nuanced humor in non-English languages like Chinese. To address this gap, w…
: "This is My SQL, Are You With Me?" A Consensus-Based Multi-Agent System for Text-to-SQL Tasks
Hanchen Xia, Feng Jiang, Naihao Deng +4
Large Language Models (LLMs) have demonstrated strong performance on various tasks. To unleash their power on the Text-to-SQL task, we propose (Review-Rebuttal-Revision), a c…