From 48f1d6f01063ecd802fc18b0cd9dd8166826ca88 Mon Sep 17 00:00:00 2001
From: Yash Singh <123385188+yashs33244@users.noreply.github.com>
Date: Fri, 19 Jun 2026 12:49:50 +0530
Subject: [PATCH] fix(reranker): clamp out-of-range LLM scores instead of
 mis-parsing them (#5635)

---
 mem0/reranker/llm_reranker.py               | 10 +++++-----
 tests/rerankers/test_llm_reranker_rerank.py | 17 +++++++++++++++++
 2 files changed, 22 insertions(+), 5 deletions(-)

diff --git a/mem0/reranker/llm_reranker.py b/mem0/reranker/llm_reranker.py
index 16d7f47c3..b89e25f4a 100644
--- a/mem0/reranker/llm_reranker.py
+++ b/mem0/reranker/llm_reranker.py
@@ -90,14 +90,14 @@ class LLMReranker(BaseReranker):
 
     def _extract_score(self, response_text: str) -> float:
         """Extract numerical score from LLM response."""
-        # Look for decimal numbers between 0.0 and 1.0
-        pattern = r'\b([01](?:\.\d+)?)\b'
-        matches = re.findall(pattern, response_text)
-        
+        # Prefer a decimal, fall back to an integer, then clamp: out-of-range outputs
+        # like "2.0"/"5" become 1.0 instead of being mis-parsed into a stray 0/1 digit.
+        matches = re.findall(r'-?\d+\.\d+', response_text) or re.findall(r'-?\d+', response_text)
+
         if matches:
             score = float(matches[0])
             return min(max(score, 0.0), 1.0)  # Clamp between 0.0 and 1.0
-        
+
         # Fallback: return 0.5 if no valid score found
         return 0.5
     
diff --git a/tests/rerankers/test_llm_reranker_rerank.py b/tests/rerankers/test_llm_reranker_rerank.py
index 607d99b1b..c7798cb1d 100644
--- a/tests/rerankers/test_llm_reranker_rerank.py
+++ b/tests/rerankers/test_llm_reranker_rerank.py
@@ -27,6 +27,23 @@ class TestExtractScore:
     def test_clamps_to_1(self, reranker):
         assert reranker._extract_score("1.0") == 1.0
 
+    @pytest.mark.parametrize(
+        "text,expected",
+        [
+            ("2.0", 1.0),
+            ("5", 1.0),
+            ("10", 1.0),
+            ("-0.3", 0.0),
+            ("-2", 0.0),
+        ],
+    )
+    def test_out_of_range_scores_are_clamped(self, reranker, text, expected):
+        assert reranker._extract_score(text) == expected
+
+    def test_decimal_score_preferred_over_leading_integer(self, reranker):
+        # A distractor integer before the score must not be picked up.
+        assert reranker._extract_score("Confidence 100%. Relevance: 0.1") == 0.1
+
 
 class TestRerank:
     def test_empty_documents(self, mock_llm):