9 papers
When Do LLMs Apply the Wrong Law? Diagnosing LLM Failures in Temporal Legal Reasoning
Yiqian Huang, Shuyuan Zheng, Qianying Liu +6
Legal reasoning tasks such as legal judgment prediction (LJP) require identifying the temporally correct version of the law governing a case -- a capability we term temporal applic…
ReverseEOL: Improving Training-free Text Embeddings via Text Reversal in Decoder-only LLMs
Ailiang Lin, Zhuoyun Li, Yusong Wang +3
Recent advances in Large Language Models (LLMs) have opened new avenues for generating training-free text embeddings. However, the causal attention in decoder-only LLMs prevents ea…
Can LLMs Be Constrained to the Past? Improving Knowledge Cutoff through Recall-Based Prompting
Michiro Asai, Ailiang Lin, Yu Kishimoto +4
Prompted knowledge cutoff instructs a large language model (LLM) to act as if information beyond a specified cutoff date were unavailable. However, prior work mainly relies on dire…
Embedding-based In-Context Prompt Training for Enhancing LLMs as Text Encoders
Ailiang Lin, Zhuoyun Li, Keyu Mao +2
Large language models (LLMs) have been widely explored for embedding generation. While recent studies show that in-context learning (ICL) effectively enhances the representational…
Causal2Vec: Improving Decoder-only LLMs as Embedding Models through a Contextual Token
Ailiang Lin, Zhuoyun Li, Yusong Wang +2
Decoder-only large language models (LLMs) have been increasingly adopted to build embedding models for diverse tasks. To overcome the inherent limitations of causal attention in re…
Minimum Bayes Risk Decoding for Error Span Detection in Reference-Free Automatic Machine Translation Evaluation
Boxuan Lyu, Haiyue Song, Hidetaka Kamigaito +5
Error Span Detection (ESD) extends automatic machine translation (MT) evaluation by localizing translation errors and labeling their severity. Current generative ESD methods typica…