52 citations · 155 across the 26 of their papers we have counts for
27 papers
EAU: Environment-Agent-User Co-evolution for Training User-Centric Agents
Min Cai, Dan Zhang, Gao Xing +3
Training LLM agents to interact with users over multiple turns is challenging because the learning signal depends not only on the agent, but also on the user simulator and environm…
Detecting and Suppressing Reward Hacking with Gradient Fingerprints
Songtao Wang, Quang Hieu Pham, Fangcong Yin +4
Reinforcement learning with verifiable rewards (RLVR) typically optimizes for outcome rewards without imposing constraints on intermediate reasoning. This leaves training susceptib…
Agentic Aggregation for Parallel Scaling of Long-Horizon Agentic Tasks
Yoonsang Lee, Howard Yen, Xi Ye +1
We study parallel test-time scaling for long-horizon agentic tasks such as agentic search and deep research, where multiple rollouts are generated in parallel and aggregated into a…
Advancing General-Purpose Reasoning Models with Modular Gradient Surgery
Min Cai, Yu Liang, Longzheng Wang +6
Reinforcement learning (RL) has played a central role in recent advances in large reasoning models (LRMs), yielding strong gains in verifiable and open-ended reasoning. However, tr…
DySCO: Dynamic Attention-Scaling Decoding for Long-Context Language Models
Xi Ye, Wuwei Zhang, Fangcong Yin +2
Understanding and reasoning over long contexts is a crucial capability for language models (LMs). Although recent models support increasingly long context windows, their accuracy o…
Language Models that Think, Chat Better
Adithya Bhaskar, Xi Ye, Danqi Chen
Reinforcement learning with verifiable rewards (RLVR) trains language models to use long chain-of-thought reasoning (CoT) in domains like mathematics and code with rule-based verif…
Query-Focused Retrieval Heads Improve Long-Context Reasoning and Re-ranking
Wuwei Zhang, Fangcong Yin, Howard Yen +2
Recent work has identified retrieval heads, a subset of attention heads responsible for retrieving salient information in long-context language models (LMs), as measured by their c…
LongProc: Benchmarking Long-Context Language Models on Long Procedural Generation
Xi Ye, Fangcong Yin, Yinghui He +5
Existing benchmarks for evaluating long-context language models (LCLMs) primarily focus on long-context recall, requiring models to produce short responses based on a few critical…
To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning
Zayne Sprague, Fangcong Yin, Juan Diego Rodriguez +7
Chain-of-thought (CoT) via prompting is the de facto method for eliciting reasoning capabilities from large language models (LLMs). But for what kinds of tasks is this extra ``thin…
LoFiT: Localized Fine-tuning on LLM Representations
Fangcong Yin, Xi Ye, Greg Durrett
Recent work in interpretability shows that large language models (LLMs) can be adapted for new tasks in a learning-free way: it is possible to intervene on LLM representations to e…
Unveiling the Impact of Coding Data Instruction Fine-Tuning on Large Language Models Reasoning
Xinlu Zhang, Zhiyu Zoey Chen, Xi Ye +4
Instruction Fine-Tuning (IFT) significantly enhances the zero-shot capabilities of pretrained Large Language Models (LLMs). While coding data is known to boost LLM reasoning abilit…
Effective Large Language Model Adaptation for Improved Grounding and Citation Generation
Xi Ye, Ruoxi Sun, Sercan Ö. Arik +1
Large language models (LLMs) have achieved remarkable advancements in natural language understanding and generation. However, one major issue towards their widespread deployment in…
MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoning
Zayne Sprague, Xi Ye, Kaj Bostrom +2
While large language models (LLMs) equipped with techniques like chain-of-thought prompting have demonstrated impressive capabilities, they still fall short in their ability to rea…
EEL: Efficiently Encoding Lattices for Reranking
Prasann Singhal, Jiacheng Xu, Xi Ye +1
Standard decoding approaches for conditional text generation tasks typically search for an output hypothesis with high model probability, but this may not yield the best hypothesis…
SatLM: Satisfiability-Aided Language Models Using Declarative Prompting
Xi Ye, Qiaochu Chen, Isil Dillig +1
Prior work has combined chain-of-thought prompting in large language models (LLMs) with programmatic representations to perform effective and transparent reasoning. While such an a…
Explanation Selection Using Unlabeled Data for Chain-of-Thought Prompting
Xi Ye, Greg Durrett
Recent work has shown how to prompt large language models with explanations to obtain strong performance on textual reasoning tasks, i.e., the chain-of-thought paradigm. However, s…
Complementary Explanations for Effective In-Context Learning
Xi Ye, Srinivasan Iyer, Asli Celikyilmaz +3
Large language models (LLMs) have exhibited remarkable capabilities in learning from explanations in prompts, but there has been limited understanding of exactly how these explanat…
Assessing Out-of-Domain Language Model Performance from Few Examples
Prasann Singhal, Jarad Forristal, Xi Ye +1
While pretrained language models have exhibited impressive generalization capabilities, they still behave unpredictably under certain domain shifts. In particular, a model may lear…
Diagnosing Ensemble Few-Shot Classifiers
Weikai Yang, Xi Ye, Xingxing Zhang +6
The base learners and labeled samples (shots) in an ensemble few-shot classifier greatly affect the model performance. When the performance is not satisfactory, it is usually diffi…
The Unreliability of Explanations in Few-shot Prompting for Textual Reasoning
Xi Ye, Greg Durrett
Does prompting a large language model (LLM) like GPT-3 with explanations improve in-context learning? We study this question on two NLP tasks that involve reasoning over text, name…
Can Explanations Be Useful for Calibrating Black Box Models?
Xi Ye, Greg Durrett
NLP practitioners often want to take existing trained models and apply them to data from new domains. While fine-tuning or few-shot learning can be used to adapt a base model, ther…
RnG-KBQA: Generation Augmented Iterative Ranking for Knowledge Base Question Answering
Xi Ye, Semih Yavuz, Kazuma Hashimoto +2
Existing KBQA approaches, despite achieving strong performance on i.i.d. test data, often struggle in generalizing to questions involving unseen KB schema items. Prior ranking-base…
Connecting Attributions and QA Model Behavior on Realistic Counterfactuals
Xi Ye, Rohan Nair, Greg Durrett
When a model attribution technique highlights a particular part of the input, a user might understand this highlight as making a statement about counterfactuals (Miller, 2019): if…
Optimal Neural Program Synthesis from Multimodal Specifications
Xi Ye, Qiaochu Chen, Isil Dillig +1
Multimodal program synthesis, which leverages different types of user input to synthesize a desired program, is an attractive way to scale program synthesis to challenging settings…