2 citations · 8 across the 45 of their papers we have counts for
47 papers
SteerSearch: Interactive Search Reasoning with Mid-Response Steering
Udit Thakur, Baohao Liao, Matteo Nulli +4
Search-augmented language models increasingly serve as long-horizon research agents, yet most open training methods assume a fixed user goal throughout search. We study mid-respons…
Last Translation Benchmark
Vilém Zouhar, Niyati Bafna, Mukund Choudhary +263
For scientific progress, we need benchmarks that test the limits of state-of-the-art models, and evaluation methods that inform us about failure cases. As models get stronger, stan…
Ladders in Chaos: When, How, (and Perhaps Why) Does Test-Time Scaling Improve LLM Machine Translation
Di Wu, Sergey Troshin, Christof Monz +2
Two forms of test-time scaling for Large Language Models (LLMs) have emerged as effective and widely adopted paradigms: sequential, in which later answer attempts depend on earlier…
Multi-Turn On-Policy Distillation with Prefix Replay
Baohao Liao, Hanze Dong, Christof Monz +3
We study on-policy distillation (OPD) for agentic tasks, where an LLM agent interacts with an environment over multiple turns and a student imitates a teacher over these multi-turn…
On the Limits of Model Merging for Multilinguality in Pre-Training
Seth Aycock, Fedor Vitiugin, Aleksandr Umnov +2
Endowing models with consistent multilingual performance can be achieved by mixing pre-training data, or post-training approaches such as language-specific model merging. In this w…
When Contextual Inference Fails: Cancelability in Interactive Instruction Following
Natalia Bila, Kata Naszádi, Alexandra Mayn +1
We investigate the separation of literal interpretation from contextual inference in a collaborative block-building tasks, where an agent must resolve underspecified instructions u…
Self-Hinting Language Models Enhance Reinforcement Learning
Baohao Liao, Hanze Dong, Xinxing Xu +2
Group Relative Policy Optimization (GRPO) has recently emerged as a practical recipe for aligning large language models with verifiable objectives. However, under sparse terminal r…
Do Language Models Reason Across Languages?
Yan Meng, Wafaa Mohammed, Christof Monz
The real-world information sources are inherently multilingual, which naturally raises a question about whether language models can synthesize information across languages. In this…
Remedy-R: Generative Reasoning for Machine Translation Evaluation without Error Annotations
Shaomu Tan, Ryosuke Mitani, Ritvik Choudhary +3
Over the years, automatic MT metrics have hillclimbed benchmarks and presented strong and sometimes human-level agreement with human ratings. Yet they remain black-box, offering li…
Reinforce-Ada: An Adaptive Sampling Framework under Non-linear RL Objectives
Wei Xiong, Chenlu Ye, Baohao Liao +6
Reinforcement learning (RL) for large language model reasoning is frequently hindered by signal loss, a phenomenon where standard uniform sampling with small group sizes fails to u…
Control the Temperature: Selective Sampling for Diverse and High-Quality LLM Outputs
Sergey Troshin, Wafaa Mohammed, Yan Meng +3
Diversity is an essential metric for evaluating the creativity of outputs generated by language models. Temperature-based sampling is a common strategy to increase diversity. Howev…
Best-of-L: Cross-Lingual Reward Modeling for Mathematical Reasoning
Sara Rajaee, Rochelle Choenni, Ekaterina Shutova +1
While the reasoning abilities of large language models (LLMs) continue to advance, it remains unclear how such ability varies across languages in multilingual LLMs and whether diff…
Lost at the Beginning of Reasoning
Baohao Liao, Xinyi Chen, Sara Rajaee +5
Recent advancements in large language models (LLMs) have significantly advanced complex reasoning capabilities, particularly through extended chain-of-thought (CoT) reasoning that…
Please Translate Again: Two Simple Experiments on Whether Human-Like Reasoning Helps Translation
Di Wu, Seth Aycock, Christof Monz
Large Language Models (LLMs) demonstrate strong reasoning capabilities for many tasks, often by explicitly decomposing the task via Chain-of-Thought (CoT) reasoning. Recent work on…
Unilogit: Robust Machine Unlearning for LLMs Using Uniform-Target Self-Distillation
Stefan Vasilev, Christian Herold, Baohao Liao +3
This paper introduces Unilogit, a novel self-distillation method for machine unlearning in Large Language Models. Unilogit addresses the challenge of selectively forgetting specifi…
The Effect of Language Diversity When Fine-Tuning Large Language Models for Translation
David Stap, Christof Monz
Prior research diverges on language diversity in LLM fine-tuning: Some studies report benefits while others find no advantages. Through controlled fine-tuning experiments across 13…
Fractured Chain-of-Thought Reasoning
Baohao Liao, Hanze Dong, Yuhui Xu +4
Inference-time scaling techniques have significantly bolstered the reasoning capabilities of large language models (LLMs) by harnessing additional computational effort at inference…
What Does Neuro Mean to Cardio? Investigating the Role of Clinical Specialty Data in Medical LLMs
Xinlan Yan, Di Wu, Yibin Lei +2
In this paper, we introduce S-MedQA, an English medical question-answering (QA) dataset designed for benchmarking large language models (LLMs) in fine-grained clinical specialties.…
Remedy: Learning Machine Translation Evaluation from Human Preferences with Reward Modeling
Shaomu Tan, Christof Monz
A key challenge in MT evaluation is the inherent noise and inconsistency of human ratings. Regression-based neural metrics struggle with this noise, while prompting LLMs shows prom…
Calibrating Translation Decoding with Quality Estimation on LLMs
Di Wu, Yibin Lei, Christof Monz
Neural machine translation (NMT) systems typically employ maximum a posteriori (MAP) decoding to select the highest-scoring translation from the distribution mass. However, recent…
ClusComp: A Simple Paradigm for Model Compression and Efficient Finetuning
Baohao Liao, Christian Herold, Seyyed Hadi Hashemi +3
As large language models (LLMs) scale, model compression is crucial for edge deployment and accessibility. Weight-only quantization reduces model size but suffers from performance…
Reward-Guided Speculative Decoding for Efficient LLM Reasoning
Baohao Liao, Yuhui Xu, Hanze Dong +5
We introduce Reward-Guided Speculative Decoding (RSD), a novel framework aimed at improving the efficiency of inference in large language models (LLMs). RSD synergistically combine…
Communicating with Speakers and Listeners of Different Pragmatic Levels
Kata Naszadi, Frans A. Oliehoek, Christof Monz
This paper explores the impact of variable pragmatic competence on communicative success through simulating language learning and conversing between speakers and listeners with dif…
Can LLMs Really Learn to Translate a Low-Resource Language from One Grammar Book?
Seth Aycock, David Stap, Di Wu +2
Extremely low-resource (XLR) languages lack substantial corpora for training NLP models, motivating the use of all available resources such as dictionaries and grammar books. Machi…