10 accepted papers
Solving math problems through verifiable languages such as Lean has significantly impacted both the mathematics and computer science communities. Current state-of-the-art models are often trained with expensive online Reinforcement Learning (RL) or expert iteration. However, these approaches rely on…
Reward models are key to language model post-training and inference pipelines. Conveniently, recent work showed that every language model defines an implicit reward model (IM-RM), without requiring any architectural changes. However, such IM-RMs tend to generalize worse, especially out-of-distributi…
Language model agents excel in long-session planning and reasoning, but existing benchmarks primarily focus on goal-oriented tasks with explicit objectives, neglecting creative adaptation in unfamiliar environments. To address this, we introduce EscapeBench—a benchmark suite of room escape game envi…
Large Language Models (LLMs) have displayed astonishing abilities in various tasks, especially in text generation, classification, question answering, etc. However, the reasoning ability of LLMs still faces many debates, especially in math reasoning. The inherent ambiguity of Natural Language (NL) l
Reward modeling is a key step in building safe foundation models when applying reinforcement learning from human feedback (RLHF) to align Large Language Models (LLMs). However, reward modeling based on the Bradley-Terry (BT) model assumes a global reward function, failing to capture the inherently d
Chain-of-thought (CoT) reasoning in large language models (LLMs) can be formalized as a latent variable problem, where the model needs to generate intermediate reasoning steps. While prior approaches such as iterative reward-ranked fine-tuning (RAFT) have relied on such formulations, they typically…
Understanding human preferences is crucial for improving foundation models and building personalized AI systems. However, preferences are inherently diverse and complex, making it difficult for traditional reward models to capture their full range. While fine-grained preference data can help, collec…
Vision-Language Models (VLMs) excel in generating textual responses from visual inputs, but their versatility raises security concerns. This study takes the first step in exposing VLMs’ susceptibility to data poisoning attacks that can manipulate responses to innocuous, everyday prompts. We introduc…
The task of modal dependency parsing aims to parse a text into its modal dependency structure, which is a representation for the factuality of events in the text. We design a modal dependency parser that is based on priming pre-trained language models, and evaluate the parser on two data sets. Compa…
As the sources of information that we consume everyday rapidly diversify, it is becoming increasingly important to develop NLP tools that help to evaluate the credibility of the information we receive. A critical step towards this goal is to determine the factuality of events in text. In this paper,…